session-summary
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No indicators of data exfiltration, remote code execution, or unauthorized credential access were found. The skill's behavior is consistent with its stated purpose of summarizing session content.\n- [PROMPT_INJECTION]: Analysis identified an indirect prompt injection surface common to summarization utilities. The skill processes session transcripts that may contain untrusted or adversarial content.\n
- Ingestion points: The skill utilizes the session_read tool to ingest session transcripts as documented in SKILL.md.\n
- Boundary markers: Absent; there are no specified delimiters or instructions to ignore instructions embedded within the session content.\n
- Capability inventory: Restricted to text analysis and structured output generation.\n
- Sanitization: No explicit sanitization or validation of the ingested transcript data is performed.
Audit Metadata