post-mortem
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from debug sessions, logs, and user descriptions to generate its reports. Ingestion points: User input, debug session breadcrumbs, and referenced bug fix materials. Boundary markers: Absent; the skill does not specify delimiters for separating processed data from instructions. Capability inventory: The skill contains instructions to interact with the JIRA API to post comments. Sanitization: Absent; no methods for sanitizing or escaping the technical data are prescribed.
- [DATA_EXFILTRATION]: The skill facilitates the transfer of documented root cause analysis to a project management system. Network operations: The workflow includes a step to post the final engineering record to a JIRA issue endpoint. This interaction is consistent with the skill's primary function of bug documentation.
Audit Metadata