spec
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill aggregates information from the conversation history and local project documentation (such as CONTEXT.md and DOMAIN-AWARENESS.md) and transmits it to GitHub to create an issue. GitHub is a well-known service, and this data flow is necessary for the skill's primary function.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and summarizes untrusted data from the conversation history and codebase.
- Ingestion points: Untrusted data is ingested from the conversation context and repository files (SKILL.md).
- Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore instructions that may be embedded in the processed data.
- Capability inventory: The skill possesses the capability to create issues on an external platform (GitHub).
- Sanitization: No explicit sanitization or validation of the synthesized content is defined in the process.
Audit Metadata