The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides functionality to verify the provenance of any git commit, including those from third-party sources. This introduces an attack surface where malicious data embedded in git commit messages, trailers, or notes could potentially influence the agent's behavior during the verification process.
Ingestion points: The node CLI verify --commit <hash> command ingests data from commit objects, trailers, and git notes (refs/notes/agent-id).
Boundary markers: No specific delimiters or instructions to ignore embedded content are described in the setup or usage.
Capability inventory: The skill possesses the capability to execute shell commands via node and git as defined in the allowed-tools frontmatter.
Sanitization: The documentation does not specify how the CLI handles potentially malicious strings within commit metadata.
[COMMAND_EXECUTION]: The skill relies on the execution of a local Node.js script (bin/cli.mjs) and the system git binary to perform core operations like signing, setup, and verification.

agent-id-git