marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from project-specific context files, which creates a surface for indirect prompt injection if those files are controlled or modified by an external actor.
- Ingestion points: The skill reads context from
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md(as specified inSKILL.md). - Boundary markers: The skill does not define clear delimiters or provide instructions to the agent to ignore any embedded commands within these context files.
- Capability inventory: While the skill itself focuses on strategy, it operates within an agent environment that typically has access to file system and shell tools.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from these external files before it is used by the agent.
Audit Metadata