release-review
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and review deployment manifests from the repository, which are external data sources.
- Ingestion points: Files located in the
deploy/**directory are ingested based on the configuration inrouting.json. - Boundary markers: The instructions in
SKILL.mddo not utilize any delimiters or system-level instructions to ignore potential commands embedded within the manifest files. - Capability inventory: No high-risk capabilities such as network operations, file writing, or subprocess execution were found in the analyzed files.
- Sanitization: There is no evidence of sanitization or validation of the manifest content before it is processed by the agent.
Audit Metadata