ClawAudit verdict

research-paper-to-ppt-v2

research-paper-to-ppt-v1

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Retrieves academic paper full text via a declared InfoX-Med API token and generates PPTX files locally; the token usage is transparently scoped to the paper-retrieval purpose with explicit fail-safe behavior when retrieval fails.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

40
security
90
transparency
70
maintenance

Findings (7)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

references/style-preferences-from-reference.md · prose

Pattern match medium

subprocess execution — runs system commands from Python

scripts/complete_pipeline.py · prose · downgraded · subprocess.run(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/fetch_fullpaper.py · prose · downgraded · http://60.205.166.229

Pattern match low

Python urllib.request — network access

scripts/fetch_fullpaper.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/fetch_fullpaper.py · prose · downgraded · os.environ.get(

Pattern match low

Python aiohttp session — async network access

scripts/medical_search_fallback_reference.py · prose · downgraded · aiohttp.ClientSession

Pattern match low

Node http/https module — low-level network access

scripts/render_pptx_from_slides.js · prose · downgraded · require('https')

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

Is this flag fair?

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