studio-distribute-scale-automate
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 content from local tracker files and project documentation, which could contain malicious instructions designed to influence the agent's behavior during the roadmap generation process.
- Ingestion points: The agent is instructed to read content from
productos/distribute/3-Growth-Experiments-Tracker.md,productos/distribute/2-Growth-Experiments.md,productos/distribute/1-Go-To-Market-Strategy.md, anddocs/PRODUCT.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' directives when processing the content of these external files.
- Capability inventory: The agent has filesystem access to read project files and write the generated roadmap to
productos/distribute/4-Scale-and-Automation-Roadmap.mdordocs/scale-automation-roadmap.md. - Sanitization: Absent. There is no explicit requirement for the agent to sanitize, validate, or filter the content extracted from the tracker files before incorporating it into the final output.
Audit Metadata