research-memory
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it reads and processes user-generated paper notes from an Obsidian vault to suggest research directions.
- Ingestion points: The
aggregate_reading.pyscript parses Markdown files from the user's vault, specifically extracting text from 'My Notes' and 'Takeaways' sections. - Boundary markers: The agent is provided with note content for summarization without specific escaping or boundary markers beyond structured JSON fields.
- Capability inventory: The
write_research_memory.pyscript has file-writing capabilities, but these are restricted to the singleresearch-memory.mdfile within the vault. - Sanitization: There is no explicit sanitization of note content; however, the skill's design mandates a multi-round interview process where the user must confirm all proposed changes.
- Mitigation: The inherent risk is effectively mitigated by the skill's structure, which prevents autonomous writing. A user must review a full unified diff preview before any changes are committed to the file system.
- [COMMAND_EXECUTION]: Static analysis detected command execution patterns in the test suite (
tests/test_research_memory_write.pyandtests/test_research_memory_aggregate.py). These are benign developer tools used for verifying the CLI interface of the scripts and are not part of the skill's runtime operations executed by the agent.
Audit Metadata