marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read context from
.claude/product-marketing-context.mdbefore interacting with the user, which presents a surface for indirect instructions to influence agent behavior. - Ingestion points: The skill ingests untrusted data from the local project file
.claude/product-marketing-context.mdas specified inSKILL.md. - Capability inventory: The agent utilizing this skill likely has access to file system operations and potentially shell execution tools, which could be targeted by instructions embedded in the context file.
- Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the content read from the context file.
- Sanitization: There is no evidence of sanitization, escaping, or validation logic applied to the content of the project-marketing-context file before it is processed by the agent.
Audit Metadata