research
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from primary sources, which creates a vulnerability to indirect prompt injection.\n
- Ingestion points: In
SKILL.md, the agent is instructed to investigate external data including "official docs, source code, specs, first-party APIs".\n - Boundary markers: The skill lacks explicit instructions or delimiters to ensure the agent ignores or segments potentially malicious commands embedded in these external sources.\n
- Capability inventory: The
SKILL.mdfile authorizes the agent to "Write the findings to a single Markdown file" within the local repository.\n - Sanitization: There is no mention of sanitization, filtering, or validation of the retrieved content before it is processed or written to the file system.
Audit Metadata