plan-validate

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from local plan files. 1. Ingestion points: plan.md and phase-*.md files are read in Step 1. 2. Boundary markers: The skill does not define clear delimiters or provide instructions to the agent to ignore any embedded commands within the data being processed. 3. Capability inventory: The agent has access to tools including Bash, TaskCreate, and AskUserQuestion in SKILL.md, which could be abused if the agent follows instructions found within the plan files. 4. Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:32 PM