session-summary
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes session history which acts as an untrusted data source.
- Ingestion points: Session transcript retrieved via the session_read tool as described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters to separate session content from its own instructions.
- Capability inventory: The skill performs text analysis and output generation; it does not have capabilities for file modification, network communication, or command execution.
- Sanitization: No explicit sanitization of the transcript content is performed before summarization.- [NO_CODE]: The skill consists purely of natural language instructions and tool configuration without any attached executable scripts or binary files.
Audit Metadata