planner-md

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a directive to 'Ideally use GPT-5.6 Luna for the subagent', which attempts to override platform model selection and influence agent behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the /grilling skill to create files, establishing an attack surface for instructions embedded in external content. 1. Ingestion points: Data from the /grilling skill referenced in SKILL.md. 2. Boundary markers (absent): There are no instructions to delimit or ignore instructions embedded within the ingested data. 3. Capability inventory: The skill can spawn subagents and perform file writes to the /plans directory. 4. Sanitization (absent): There is no mention of sanitizing or escaping the data before it is written to markdown files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:34 PM