skills/buildgreatproducts/product-os-public/studio-distribute-activation-retention-audit/Gen Agent Trust Hub
studio-distribute-activation-retention-audit
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user's application codebase and interpolates it into a generated audit report and a 'fix prompt'. A malicious actor could embed instructions within the codebase that attempt to influence the agent's output or the subsequent instructions given to a coding agent.
- Ingestion points: The skill reads the entire application repository (specifically the
productos/directory) and various documentation files (docs/PRODUCT.md,productos/design/*.md). - Boundary markers: The instructions do not define delimiters or specific 'ignore embedded instructions' warnings for the agent to use when analyzing the codebase.
- Capability inventory: The skill has the capability to write a report to the filesystem (
docs/ACTIVATION-RETENTION-AUDIT.md) and generate complex prompts for other agents. - Sanitization: There are no specific instructions for escaping or validating the content of the files read from the repository before they are summarized in the output.
Audit Metadata