execute-spec

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands defined within the processed specification file.\n
  • Evidence: "Execute all commands from the spec's 'Validation Commands' section" in SKILL.md.\n
  • Evidence: "Run the component's check command (or the spec's inner-loop command)" in SKILL.md.\n- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing and acting upon instructions in specification files.\n
  • Ingestion points: Reads specification files from paths like docs/ideation/*/spec-phase-*.md as described in SKILL.md.\n
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore potentially malicious instructions within the spec.\n
  • Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, Agent, TaskCreate, and TaskUpdate.\n
  • Sanitization: Absent. The skill follows the specification "literally" and implements the provided technical approach without validating the commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 03:25 PM