The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze an entire service codebase, including configurations and documentation. This large ingestion surface creates a risk where malicious instructions embedded in the analyzed repository could attempt to influence the agent's audit behavior.
Ingestion points: Accesses service entry points, worker processes, migrations, configurations, deploy manifests, and local standards documentation (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the analyzed code from the agent's core instructions.
Capability inventory: The skill has access to several powerful tools including execute_command, write_file, run_build, and run_tests (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the content being analyzed before it is processed by the model.
[COMMAND_EXECUTION]: The skill uses the execute_command and run_build tools to perform audits. It explicitly mentions running third-party security and reliability tools such as Grype, Trivy, LitmusChaos, and Toxiproxy to verify the release artifact's safety and resilience.

review-service