speckit-checklist

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh during the setup phase to identify the feature directory and available documentation.
  • [COMMAND_EXECUTION]: The skill performs file system operations, including creating a checklists/ directory and writing new markdown files within the identified FEATURE_DIR.
  • [DATA_EXFILTRATION]: The agent reads local documentation files (spec.md, plan.md, tasks.md) to extract requirements for checklist generation. No network operations or external data transfers were detected.
  • [PROMPT_INJECTION]: The skill includes instructions to the agent to interpret user input and documentation, but these are instructional constraints for its primary function rather than malicious bypass attempts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local markdown files. However, it implements a strategy to load only necessary portions and summarize content, which mitigates the risk of processing large-scale malicious instructions embedded in documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:10 PM
Security Audit — agent-trust-hub — speckit-checklist