signup
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and trust content from external files (e.g.,
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md) to gain context before interacting with the user. This creates a surface for indirect prompt injection if these files contain malicious instructions designed to override agent behavior. - Ingestion points: The 'Initial Assessment' section in
SKILL.mddirects the agent to read product marketing context files. - Boundary markers: The instructions do not specify using delimiters or 'ignore embedded instructions' warnings when processing the content of these files.
- Capability inventory: Based on the provided files, the skill is advisory and does not utilize sensitive capabilities like network operations, shell execution, or file writing.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the content read from the external marketing files.
Audit Metadata