gaps
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external gap-tracker.yaml file which could contain instructions intended to manipulate the agent's behavior during reporting or status updates.
- Ingestion points: The agent reads data from ~/.claude/plugins/config/claude-for-legal-zh/regulatory-legal/gap-tracker.yaml.
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the tracker data.
- Capability inventory: The skill performs file read and write operations, including updating gap statuses and recording reasons on the local filesystem.
- Sanitization: No sanitization or validation logic is defined for the YAML content processed by the agent.
Audit Metadata