watch
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for monitoring external research data, which is a potential surface for indirect prompt injection if untrusted data is processed by the agent.\n
- Ingestion points: External research papers, field updates, and alert data mentioned in SKILL.md.\n
- Boundary markers: None identified in SKILL.md.\n
- Capability inventory: Writing results to the 'outputs/' directory as mentioned in SKILL.md.\n
- Sanitization: No sanitization or filtering logic is defined in SKILL.md.\n- [NO_CODE]: The file SKILL.md contains only documentation and frontmatter metadata. No actual code, scripts, or prompt templates were provided for analysis.
Audit Metadata