session-memory
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing data that could contain malicious instructions.
- Ingestion points: The skill accepts findings from 'any skill output: copy-pasted report, file reference, or inline conversation output' (SKILL.md, Step 1) and loads structured session markdown files from the filesystem (SKILL.md, Steps 2-4).
- Boundary markers: The instructions lack requirements for the agent to use specific delimiters or 'ignore embedded instructions' warnings when parsing external content.
- Capability inventory: The skill utilizes file system operations including reading files, writing new session files, and deleting old sessions (pruning) within the .ds-ops/sessions/ directory (SKILL.md).
- Sanitization: No logic is provided to sanitize, escape, or validate the content extracted from skill outputs before it is interpolated into the session history or used for trend analysis.
Audit Metadata