sentinel-status
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the 'sentinel' CLI and 'git' commands to retrieve system health, repository status, and statistics.
- Evidence: Execution of
sentinel doctor,sentinel stats,git -C .sentinel/shared status -sb, andgit -C .sentinel/shared log --oneline -3in SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local JSON state files that describe Sentinel runs. If these files incorporate content from untrusted external sources (e.g., commit messages or process logs tracked by Sentinel), they could be used to inject instructions.
- Ingestion points: Reads from
.sentinel/runs/*/state.jsonin SKILL.md. - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions within the JSON content.
- Capability inventory: Access to shell execution through the
sentinelandgitcommands. - Sanitization: Absent; the skill does not specify any validation or sanitization for the state data before the agent processes it.
Audit Metadata