studio-distribute-gtm-strategy
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external repository files to gather product context, which creates a potential vulnerability if those files contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads
docs/PRODUCT.md, files within theproductos/define/directory, and codebase manifests such aspackage.jsonorREADMEfiles (File: SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing these external files.
- Capability inventory: The skill possesses the ability to read and write files, as well as perform web searches to research distribution channels.
- Sanitization: There is no evidence of content sanitization, validation, or filtering for the data ingested from the repository before it is used to formulate the strategy output.
Audit Metadata