discuss-connection
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are focused on cognitive note-taking workflows and user interaction. All file operations (reading and writing) are restricted to the local vault environment as described in the skill's purpose. The skill uses a manual trigger and requires direct user input to initiate, reducing the risk of automated exploitation.
- [PROMPT_INJECTION]: The skill processes content from existing notes to synthesize new ideas, which is a potential surface for indirect prompt injection if source notes contain instructions intended to influence the agent.
- Ingestion points: Reads user-specified notes from the vault.
- Boundary markers: Note content is processed as part of the discussion without specific delimiters.
- Capability inventory: The skill can read local files and write or append to the file system.
- Sanitization: No specific filtering or escaping of note content is required by the instructions.
Audit Metadata