The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides scripts/audit.sh, which executes shell commands to analyze the target repository's structure and code patterns using standard utilities like grep, find, and git.
[COMMAND_EXECUTION]: The scripts/audit.sh script, when invoked with the --probe flag, executes go test on detected integration packages. This execution is part of the intended audit process but involves running code from the repository under analysis.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted data from external repositories, presenting a surface for indirect prompt injection.
Ingestion points: The scripts/audit.sh script and the agent's audit workflow read file contents, metadata, and configuration from the target repository root.
Boundary markers: No explicit delimiters or boundary markers are used when the agent or the script ingests data for analysis.
Capability inventory: The skill possesses the capability to read, write, and execute shell commands (via the Bash tool and scripts/audit.sh).
Sanitization: The skill does not implement specific sanitization or filtering for the content ingested from the target repository before processing.

reality-gate