to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill performs standard repository analysis and documentation tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads data from the repository and has the capability to publish results to an external issue tracker.
- Ingestion points: The agent is instructed to explore the repository to understand the current state of the codebase (SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the repository files are provided.
- Capability inventory: The agent can read files and use tools to publish to the project issue tracker.
- Sanitization: No explicit sanitization of the ingested repository content is mentioned before it is synthesized into the specification.
Audit Metadata