The Agent Skills Directory

[COMMAND_EXECUTION]: Executes the agent-validate status CLI command to retrieve high-level session-level data and gate results.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from log files generated by external tools without sanitization.
Ingestion points: Reads log files (check_*.log) and JSON files (review_*.json) as specified in SKILL.md.
Boundary markers: Absent; no delimiters or warnings are used when reading external file content.
Capability inventory: Includes Bash for command execution and Read for file system access.
Sanitization: Absent; the content is extracted and presented directly in the report.

validator-status