BC gmail-skill
Gmail automation: summarize, labels, spam purge, filing, deletion, permanent delete
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-autorun-instructionSKILL.md:19Instructs the agent to auto-run a script on every session2. **ALWAYS run the script.** Every capability below has a specific command. You MUST execute it. Do NOT skip execution based on assumptions or prior results.
-
medium Dangerous commands
cmd-autorun-instructionSKILL.md:83Instructs the agent to auto-run a script on every session**ALWAYS use background mode. ALWAYS run the script. NEVER skip it.**
-
low Dangerous commands
cmd-background-processbins/gmail-background-task.sh:61Starts a background / autostarted process (code comment)# Uses nohup + subshell + disown to survive agent/parent process death
comment -
low Dangerous commands
cmd-background-processbins/gmail-background-task.sh:176Starts a background / autostarted processdisown
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 17 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 13 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1876 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +3Description length 83: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.