BF equity-research-analyst
Use when the user asks for institutional-style equity research on a public company, ETF, or TradingView-resolvable ticker, including initiation reports, earnings updates or previews, catalyst calendars, morning notes, sector or peer overviews, thesis reviews, model refreshes, and stock screening or idea generation.
As a process F 68/100 · Will not run — References files that are not bundled: references/tradingviewapi-docs/openapi.json
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.
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
- The text references files that are not there: add them or drop the references.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-shell-rcreferences/tradingviewapi-docs/README.md:76Writes to a shell startup fileecho 'export RAPIDAPI_KEY="your_key_here"' >> ~/.zshrc
-
medium Exfiltration
net-credential-usereferences/tradingviewapi.md:146Credential used in a network call (verify the destination is the intended service)curl -H "x-rapidapi-key: $RAPIDAPI_KEY" \
-
medium Exfiltration
net-credential-usereferences/tradingviewapi.md:203Credential used in a network call (verify the destination is the intended service)curl -H "x-rapidapi-key: $RAPIDAPI_KEY" \
-
medium Exfiltration
net-credential-usereferences/tradingviewapi.md:207Credential used in a network call (verify the destination is the intended service)curl -H "x-rapidapi-key: $RAPIDAPI_KEY" \
-
medium Exfiltration
net-credential-usereferences/tradingviewapi.md:227Credential used in a network call (verify the destination is the intended service)curl -H "x-rapidapi-key: $RAPIDAPI_KEY" \
-
medium Exfiltration
net-credential-usereferences/tradingviewapi.md:231Credential used in a network call (verify the destination is the intended service)curl -H "x-rapidapi-key: $RAPIDAPI_KEY" \
Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/tradingviewapi-docs/openapi.json
Process rating: all ten parameters 68/100
- 0Tools and files. 1 referenced file(s) missing: references/tradingviewapi-docs/openapi.json
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 34 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2154 tokens
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)
- +1No license
- +2Single-language instructions
- +3Description length 316: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.