gsd-new-milestone
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill accepts a milestone name via the
$ARGUMENTSparameter and reads existing project data from.planning/PROJECT.md. - Boundary markers: There are no explicit delimiters or instructions defined to treat ingested content as data only or to ignore embedded commands.
- Capability inventory: The skill is granted powerful capabilities including the
Bashtool, fileWriteaccess, and the ability to delegate tasks to sub-Agentinstances. - Sanitization: No input validation, escaping, or content filtering is specified before the data is interpolated into the workflow context.
Audit Metadata