qa-project-memory
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as a centralized logging system that ingests and persists data from various other AI agent skills and external task outputs into markdown files within the
docs/qa-memory/directory. - Ingestion points: The
updatecommand and the associated Post-Task Protocol read and process outputs from an ecosystem of QA skills (e.g., test generators, bug ticket creators, flaky detectors). - Boundary markers: The skill does not implement specific delimiters or instructions to ignore potential commands embedded within the logs it records.
- Capability inventory: The skill possesses the capability to write and append to files in the project workspace, creating a persistent 'memory' that is explicitly checked before subsequent tasks.
- Sanitization: There are no instructions or mechanisms for sanitizing or escaping the text produced by other skills before it is interpolated into the memory files, creating a surface where malicious instructions could be stored and later executed by the agent or other skills reading the log.
Audit Metadata