speckit-clarify

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh to identify feature directories and specification paths. The instructions include specific guidance on escaping user-provided arguments to prevent shell injection, which is a positive security practice.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes the content of specs/<feature>/spec.md, which could contain untrusted data.
  • Ingestion points: The file specs/<feature>/spec.md is loaded and scanned in Step 2 of the workflow.
  • Boundary markers: The workflow does not specify explicit delimiters or 'ignore' instructions for the specification content during the scanning phase.
  • Capability inventory: The agent has the capability to execute a local bash script (Step 1) and perform file writes to the specification file (Step 7).
  • Sanitization: The skill provides instructions for escaping shell arguments but does not explicitly describe sanitization of the specification content itself before internal processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — speckit-clarify