speckit-tasks

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local bash script at .specify/scripts/bash/check-prerequisites.sh. This is a vendor-provided script used to detect project structure and is consistent with the skill's stated purpose of project analysis.
  • [PROMPT_INJECTION]: The skill ingests content from external markdown design documents to generate its output, presenting a surface for indirect prompt injection.
  • Ingestion points: Reads multiple project documentation files from specs/<feature>/, such as plan.md and spec.md.
  • Boundary markers: The skill does not define specific delimiters or "ignore instructions" headers when processing the content of these files.
  • Capability inventory: The skill possesses the ability to execute local shell scripts and write files to the repository.
  • Sanitization: No explicit sanitization or validation logic is defined for the data extracted from the design artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:14 AM
Security Audit — agent-trust-hub — speckit-tasks