memo-coach
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill automates the creation and saving of research memos to the local filesystem, specifically targeting the
~/Documents/research-memos/directory. This behavior is documented as the core functionality for researchers and is not used for malicious system modification. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill handles user-provided research data but does not include any network capabilities, external URLs, or instructions to transmit data to remote servers.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research data to populate its templates, creating a potential surface for indirect injection.
- Ingestion points: User input captured during the Open, Axial, and Selective coding questioning phases.
- Boundary markers: The skill utilizes Markdown blockquotes and structured YAML frontmatter to delimit user-provided content within the generated memo files.
- Capability inventory: File system write operations are limited to the user's document folder.
- Sanitization: The instructions explicitly mandate that the agent must use the researcher's responses verbatim without adding AI-generated analysis or modifying the user's vocabulary.
Audit Metadata