research
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and synthesize information from external, untrusted primary sources such as documentation and source code. This exposes the agent to indirect prompt injection vulnerabilities if those sources contain malicious instructions.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to read official docs, source code, specs, and first-party APIs. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions found within the researched materials.
- Capability inventory: The skill involves writing Markdown files to the local repository.
- Sanitization: There are no instructions for sanitizing, validating, or filtering the content retrieved from external sources before processing it or writing it to disk.
Audit Metadata