planning-workflows

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided requirements to generate documentation and implementation plans, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: User requirements entering the workflow as described in references/source-commands.md.\n
  • Boundary markers: No explicit delimiters or boundary markers for isolating user-supplied requirement text were found.\n
  • Capability inventory: The skill utilizes the interactiveDialog tool and performs file system writes to the specs/ directory.\n
  • Sanitization: No sanitization or validation mechanisms for user-provided text are implemented in the logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 04:57 PM
Security Audit — agent-trust-hub — planning-workflows