analyze-findings
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data during its workflow, creating a surface where malicious instructions in the input could influence the agent.
- Ingestion points: The skill reads SARIF results from
.opentaint/results/report.sarif, finding definitions from.opentaint/tracking/findings/*.yaml, and project source code from.opentaint/project/sources/. - Boundary markers: Absent. The instructions do not provide explicit delimiters or "ignore embedded instructions" warnings when processing the contents of reports or source code.
- Capability inventory: The skill is authorized to read project files and write triaged findings back to YAML files in the tracking directory. It does not appear to use network or arbitrary shell execution tools in its defined workflow.
- Sanitization: Absent. There are no instructions to sanitize or escape data ingested from the SARIF reports or source code before the agent processes it to make a triage decision.
Audit Metadata