goals
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process data from untrusted external sources, creating a risk that malicious instructions embedded in that data could influence the agent's behavior.
- Ingestion points: The skill reads external signals from email, recruiter communications, and messaging history across multiple category files (e.g.,
creation/career.md,creation/relationships.md, andcreation/productivity.md). - Boundary markers: The skill lacks instructions for using delimiters or explicit "ignore embedded instructions" warnings when processing these external data streams.
- Capability inventory: The agent has capabilities to write persistent data to the user's memory (
~/MEMORY.mdviamuse.edit) and manage goal records (user_goal.create,user_goal.update,user_goal.create_entry). - Sanitization: There are no mentioned protocols for sanitizing or validating external content before it is interpolated into prompts or stored in the user's profile.
Audit Metadata