walkthrough
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted external data such as source code, pull requests, and documentation. This creates a surface where malicious instructions embedded in those artifacts could potentially influence agent behavior.
- Ingestion points: Artifacts specified in
SKILL.mdinclude source code, diffs, pull requests, architecture documents, APIs, data models, tests, and build/deploy flows. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate analyzed content from the agent's core logic.
- Capability inventory: The skill is primarily focused on instructional walkthroughs. In specific environments, it uses the
doctrinetool for data retrieval and references apairskill for performing code modifications. - Sanitization: There are no instructions for sanitizing, validating, or escaping the external content before it is processed or displayed.
Audit Metadata