rca-report
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill is designed for incident documentation and explicitly instructs the agent not to capture sensitive credentials.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data to generate local files, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Ingests external data such as conversation logs, system transcripts, and user notes during the investigation phase (documented in SKILL.md).\n
- Boundary markers: Uses structured Markdown templates (templates/rca-report.md) with distinct sections and code blocks to separate data.\n
- Capability inventory: The skill writes generated reports to the local file system in the current working directory as specified in SKILL.md.\n
- Sanitization: Does not implement specific sanitization of ingested logs before interpolation into the Markdown report templates.
Audit Metadata