deep-research
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate research workflow and follows best practices for sourcing and attribution.
- [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection as it ingests untrusted data from the public web. However, the risk is mitigated by the skill's limited capability set.
- Ingestion points: Untrusted data enters the context via
firecrawl_scrapeandcrawling_exain Step 4. - Boundary markers: Absent. The skill instructions do not define specific delimiters or instructions to ignore embedded commands within crawled content.
- Capability inventory: Capabilities are limited to web searching, scraping, and writing the final markdown report to a file. There are no subprocess execution, credential access, or arbitrary shell capabilities.
- Sanitization: Absent. The skill does not describe any specific sanitization or filtering of external content before processing.
- [DATA_EXFILTRATION]: No exfiltration patterns were found. Network activity is scoped to the primary purpose of the skill (web research) using dedicated tool interfaces.
Audit Metadata