Caveat verdict

depradar

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND writes files

Dependency breaking-change analysis tool that reads local dependency files, checks public registries, and searches community resources; all actions are transparent and consistent with the stated intelligence-gathering purpose.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Capability combination high

Accesses agent memory AND writes files — may modify agent behavior persistently

LLM01 · LLM06 · ASI01 · ASI06

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Accesses agent memory/configuration files

agent_memory

Findings (17)

Pattern match critical

Pipe to python — executes piped content as Python code

README.md · code · | python

Pattern match critical

Recursive delete from root or home — destructive command

README.md · code · rm -rf ~

Pattern match high

Possible hardcoded credential

hooks/scripts/check-config.sh · prose · downgraded · TOKEN="${GITHUB_TOKEN:-}

Pattern match high

Accesses sensitive system files

tests/test_production_fixes.py · prose · downgraded · /etc/passwd

Pattern match medium

Popular HTTP library — network access

SKILL.md · code · axios

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

References agent configuration files

CLAUDE.md · code · CLAUDE.md

Pattern match medium

Instructs covert action — may act without user awareness

README.md · prose · downgraded · quietly

Pattern match medium

Dynamic import() — loads module at runtime

scripts/lib/js_ast_helper.js · prose · downgraded · import('

Pattern match medium

subprocess execution — runs system commands from Python

tests/test_smoke.py · prose · downgraded · subprocess.run(

Pattern match low

Accesses sensitive environment variables

fixtures/github_issues_sample.json · prose · downgraded · process.env.WEBHOOK_SECRET

Pattern match low

Python os.environ.get — reads environment variable

scripts/lib/cache.py · prose · downgraded · os.environ.get(

Pattern match low

Python urllib.request — network access

scripts/lib/crates_registry.py · prose · downgraded · urllib.request

Pattern match low

References webhook/callback URL

scripts/lib/notify.py · prose · downgraded · WEBHOOK_URL

Pattern match low

Python threading.Timer — deferred execution

scripts/lib/usage_scanner.py · prose · downgraded · threading.Timer(

Pattern match low

Python shutil file operation — copies/moves/deletes files

tests/test_cache.py · prose · downgraded · shutil.rmtree(

Pattern match low

importlib.import_module — dynamic module loading

tests/test_esm_alias.py · prose · downgraded · importlib.import_module(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_incredential_accessagent_memoryfile_write
Check another skill Browse the registry Auditing your own skills or configs? Use the API