ops-rca-hypothesis-generator
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill processes structured JSON data locally to generate hypotheses based on time and keyword proximity. No network access, remote code downloads, or command execution patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from incident and change logs.
- Ingestion points: The
--incidentand--changesJSON files processed inops_rca_hypothesis_generator.py. - Boundary markers: Absent; the data is read directly from the JSON structure without specific prompt delimiters.
- Capability inventory: The skill is limited to reading local files and writing the output to a specified JSON path via
open()inops_rca_hypothesis_generator.py. - Sanitization: Input text is sanitized during processing via regex (
[a-z0-9]{3,}) to extract keywords, which effectively strips potentially malicious instruction fragments before scoring logic is applied.
Audit Metadata