session-logger
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session transcripts and conversation history which are untrusted external inputs. Ingestion points: The skill reads host-provided JSONL transcripts and manual session summaries (SKILL.md). Boundary markers: The skill instructs the agent to create bounded and compact recovery artifacts rather than durable raw memory (SKILL.md). Capability inventory: The skill uses Read and Write tools to process transcripts and save summaries (frontmatter). Sanitization: The instructions include a dedicated Privacy and Safety section that mandates redacting credentials, tokens, private keys, and emails before storage (SKILL.md).
Audit Metadata