context-layer-health-check
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git merge logs which could potentially contain malicious instructions.
- Ingestion points: Reads merge commit messages from
git log --mergesinSKILL.mdto identify priority signals. - Boundary markers: Absent. There are no instructions or delimiters defining the boundary between the agent's instructions and the data retrieved from the logs.
- Capability inventory: The agent is authorized to modify files to fix identified issues and execute shell commands (
scripts/lint). - Sanitization: Absent. The skill does not provide mechanisms to sanitize or ignore instructions potentially embedded within the log entries.
- [COMMAND_EXECUTION]: The skill executes local scripts as part of its verification process.
- Evidence: The instructions explicitly require running
scripts/lintandscripts/lint --reportto finish the task.
Audit Metadata