session-summary
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the local environment and conversation logs.\n
- Ingestion points: The agent reads conversation history, notes, repository artifacts, and file contents (SKILL.md).\n
- Boundary markers: The instructions do not define specific delimiters to isolate summarized content from agent instructions.\n
- Capability inventory: The skill involves reading local project files and writing summary files to a
.summaries/directory (SKILL.md).\n - Sanitization: No explicit sanitization or filtering is performed on the ingested data.
Audit Metadata