research
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources and perform file system writes, establishing a classic indirect prompt injection surface.
- Ingestion points: The agent reads from "official docs, source code, specs, first-party APIs" as specified in
SKILL.md. These are externally controlled sources that could contain adversarial instructions. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions found within the researched materials.
- Capability inventory: The skill allows the agent to write Markdown files to the local repository filesystem.
- Sanitization: There is no evidence of filtering or sanitization of the external content before it is written to the repository or processed by the agent.
Audit Metadata