CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

30.8 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 1 flagged

Securityscore 88 · 1 finding

MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · README.md

MEDIUM — it fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.

Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted

excerptREADME.md· markdown

730- Never commit `update_hr_contacts.py` to Git (contains real recruiter names/LinkedIn URLs)

731- Keep your Gmail App Password secure

732- Don't share your Excel tracker if it contains private data

733

734## Acknowledgements

Occurrences

1 occurrence · at L732

How to fix

Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.

Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-IMPERATIVE-01sha256d9839cdc44f5a183…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.claude/skills/fit-check/SKILL.md · 1 file

.claude/skills/fit-check/SKILL.md1.2 KB · Markdown

name: fit-check

description: Score a job posting's fit against your resume using Gemini. Fetches the full job description and returns a score, strengths, gaps, and recommendation. Triggers on phrases like "fit-check <url>", "is this a good fit <url>", "check fit for <url>", "score this job <url>".

Fit Check

Run a job fit analysis against the user's resume using fit_check.py.

Trigger

User says fit-check <url> or pastes a job URL asking "is this a good fit" / "check fit".

Steps

Extract the URL from the user's message.
Optionally extract --title and --company if the user mentioned them.
Run from the project root:

cd C:\Users\mahas\Learnings\claude-job-agent
python fit_check.py "<url>" [--title "..."] [--company "..."]

Show the output to the user.
If the score is Weak or Moderate, offer a brief 1-line note on whether it's still worth applying (e.g. if it's a stretch role they want to aim for).

Notes

fit_scorer.py must be in the same directory (it is).
FIT_SCORE_ENABLED = True must be set in config.py (default is True).
WTTJ and BuiltIn URLs are supported. LinkedIn guest API is also supported.
If description fetch fails, the score is title-only — the output will say so.

fit-check— agent skill

Is fit-check safe to install?

Fit Check

Trigger

Steps

Notes

Audit the pieces. Scan the whole. Decide.