pdf-extract-shell-first
PDF text extraction with tool cascade prioritizing shell pdftotext before Python fallback
60
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./benchmarks/gdpval/skills/pdf-download-extract-fallback-enhanced-e27e0c/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes downloading a PDF from a runtime-supplied web URL via `curl` (Step 0 / script Step 0), and the extracted PDF text is then loaded back into the LLM context via `read_file` from `output.txt` (Step 2/3), so outsider-authored content from arbitrary URLs can become LLM-readable prose.
- Repository
- HKUDS/OpenSpace
- Commit
3827781
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.