skills/cruldra/skills/writing-plans/Gen Agent Trust Hub

writing-plans

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external data. Ingestion points: Specification files are read from SPEC_FILE_PATH to guide the planning and review process. Boundary markers: No delimiters or instructions to disregard embedded commands are present in the prompts that ingest specifications. Capability inventory: The skill is designed to write implementation plans to the docs/plans/ directory on the local filesystem. Sanitization: No validation or sanitization logic is implemented for the specification content.
  • [SAFE]: No other security concerns such as hardcoded credentials, malicious network operations, or obfuscated commands were detected in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:42 PM