al
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a mandatory directive to "Do not use your plan mode," which explicitly overrides the agent's standard operational procedures and planning workflows.
- [PROMPT_INJECTION]: The skill instructs the agent to ingest and prioritize instructions from a relative path (
../alignfirst/SKILL.md) outside of its own directory, establishing an unverified instruction chain.
Audit Metadata