comments-docs
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external code files, creating a surface for indirect prompt injection where malicious instructions in the code could attempt to influence the agent's behavior.
- Ingestion points: File content is read into the context using the Read tool based on user-provided arguments in SKILL.md.
- Boundary markers: There are no explicit markers or instructions to isolate the ingested code or to tell the agent to ignore any potential instructions within that code.
- Capability inventory: The skill frontmatter restricts the agent to using only the Read and Grep tools (SKILL.md), providing no mechanism for file modification or network communication.
- Sanitization: The skill does not perform any validation or sanitization of the content retrieved from the target files.
Audit Metadata