FB clawback
Mirror congressional stock trades with automated broker execution and risk management. Use when you want to track and automatically trade based on congressional disclosures from House Clerk and Senate eFD sources.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 13
-
high Dangerous commands
cmd-persistencescripts/setup_cron.sh:61Persistence mechanism (cron / launchd / scheduled task / autorun registry)EXISTING=$(crontab -l 2>/dev/null | grep -c "run_bot.sh")
-
high Dangerous commands
cmd-persistencescripts/setup_cron.sh:74Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "# Congressional Trade Mirror Bot") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup_cron.sh:75Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$DAILY_CHECK") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup_cron.sh:76Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$HOURLY_MONITOR") | crontab -
Medium and low: 9
-
medium Dangerous commands
cmd-persistencescripts/setup_cron.sh:66Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l 2>/dev/null | grep -v "run_bot.sh" | crontab -
detector -
medium Exfiltration
exfil-webhook-urlsrc/clawback/congress_data/alert_manager.py:201Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{bot_token}/sendMessage"quoted -
medium Exfiltration
exfil-webhook-urlsrc/clawback/notifications.py:18Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)self.base_url = f"https://api.telegram.org/bot{bot_token}"quoted -
medium Exfiltration
exfil-webhook-urlsrc/clawback/telegram_notifier.py:94Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{self.bot_token}/sendMessage"quoted -
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:58Mentions editing / listing crontabcrontab -l > /tmp/crontab_backup_$(date +%Y%m%d_%H%M%S).txt 2>/dev/null
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:61Mentions editing / listing crontabEXISTING=$(crontab -l 2>/dev/null | grep -c "run_bot.sh")
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:66Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -v "run_bot.sh" | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:74Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "# Congressional Trade Mirror Bot") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:75Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$DAILY_CHECK") | crontab -
Files scanned: 53. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 86 steps, 1 vague phrases
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2994 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 213: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 86 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.