sentinel-resume
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
sentinel resume <slug>command to interact with the Sentinel environment. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads the files
.sentinel/runs/<slug>/decisions.mdand*-result.mdto determine the state and next steps of a run (in SKILL.md). - Boundary markers: There are no explicit boundary markers or instructions to treat the content of these files as untrusted data.
- Capability inventory: The skill can execute the
sentinelcommand and perform file system operations (listing and reading files). - Sanitization: No validation or sanitization is performed on the content of the ingested markdown files before the agent follows their instructions to continue the pipeline.
Audit Metadata