to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the conversation history and repository content to generate output for an external system.
- Ingestion points: Accesses the current conversation context and performs repository exploration to understand the codebase state (SKILL.md).
- Boundary markers: Absent. The instructions do not provide delimiters or specific warnings to the model to ignore instructions embedded within the codebase or conversation logs.
- Capability inventory: The skill is designed to publish the synthesized specification directly to the project's issue tracker and apply triage labels (SKILL.md).
- Sanitization: Absent. There is no logic specified to escape or validate the content gathered from the repo or conversation before it is published to the issue tracker.
Audit Metadata