resilient-research-workflow
Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output
59
74%
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/spreadsheet-proof-gate-merged/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
Phase A delegates to `shell_agent` to perform web research (including direct URL fetching / API calls), so at runtime the LLM context is likely to ingest outsider-authored web page text and scraped content as free-form narrative data.
- 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.