gaps-author
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow involves executing a local script
python3 scripts/validate-gaps.pyto validate generated YAML files. The command uses a<process-id>parameter derived from user input, which could serve as a command injection surface if not properly handled by the agent.- [PROMPT_INJECTION]: The skill ingests untrusted data to extract process information, creating an indirect prompt injection surface. - Ingestion points: Processes supplied process notes, policy text, workflows, and implementation artifacts provided by the user.
- Boundary markers: Absent; no delimiters or 'ignore embedded instructions' warnings are specified for the agent.
- Capability inventory: Shell command execution (via a Python validation script) and file system write operations.
- Sanitization: No explicit sanitization, validation, or filtering of the ingested external content is described before processing.
Audit Metadata