The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, including scripts and manifests, which could be leveraged to influence the agent's output. • Ingestion points: The skill reads repository configurations, deployment manifests, and script contents discovered via ripgrep commands in SKILL.md. • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions. • Capability inventory: The agent can execute shell commands (rg) and perform file read operations. • Sanitization: There is no evidence of validation or sanitization of the file content before it is processed into the runbook format.
[COMMAND_EXECUTION]: The skill executes the ripgrep (rg) command to search for configuration details and health check patterns. • Evidence: Multiple rg commands are used to find container files, CI/CD workflows, and specific strings like "DATABASE_URL" and "health".

runbook-generator