writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process content from various repository files, creating a surface where untrusted data in those files could influence the agent's actions.
- Ingestion points: The 'Reads' section in
SKILL.mdspecifies that the agent should readAGENTS.md,CLAUDE.md,package.json, and repository-specific constraint files likedocs/agents/project.md. - Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions that might be embedded within the content of these files.
- Capability inventory: The skill is intended to guide the agent while it performs file-writing tasks, specifically 'creating or editing skills, or modifying AGENTS.md or CLAUDE.md'.
- Sanitization: There are no requirements for the agent to sanitize, validate, or filter the content retrieved from the external files before using it to inform its writing process.
Audit Metadata