investigate
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to process and synthesize external research data, such as interview transcripts, survey responses, and observation notes. This creates a vulnerability surface where an attacker providing the research data could embed malicious instructions to influence the agent's synthesis or subsequent output.
- Ingestion points: External qualitative and quantitative data processed during affinity mapping and thematic analysis (SKILL.md, Section 5: Synthesis frameworks).
- Boundary markers: The skill emphasizes evidence-based reporting and data citation, but does not provide technical delimiters or instructions to ignore embedded commands within the research data.
- Capability inventory: The skill specifies file-write operations to save research plans, guides, and finding reports to the local working directory. No subprocess calls or network exfiltration tools are used.
- Sanitization: The instructions do not include steps for sanitizing or escaping the content of external research findings before they are processed or included in deliverables.
Audit Metadata