stack-researcher
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to conduct web research on technology components using sources like NVD, GitHub advisories, and vendor blogs. This creates a surface where an attacker could potentially influence the agent's behavior by placing malicious instructions in a public advisory or blog post.
- Ingestion points: Web research findings from external, untrusted sources described in Step 2 of SKILL.md.
- Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to ignore instructions embedded in the external research data.
- Capability inventory: File system write operations to the
engagements/directory (SKILL.md). - Sanitization: Absent. No explicit validation or filtering is required for the content fetched from the internet before it is processed and written to engagement files.
Audit Metadata