starlight-devex-review
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external interface definitions, examples, and documentation for review. If these inputs contain malicious instructions, they could influence the agent's behavior during the review process. * Ingestion points: The 'Inputs' section (SKILL.md) specifies that the skill takes interface definitions and examples provided at runtime. * Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore instructions embedded within the data being reviewed. * Capability inventory: The skill is authorized to 'Test commands and examples in a supported environment' (SKILL.md). * Sanitization: No sanitization or validation of the input examples is described.
- [COMMAND_EXECUTION]: The workflow explicitly directs the agent to execute commands and examples found in the provided inputs to verify their functionality. While this is a functional requirement of the skill, it represents a runtime execution surface for content derived from potentially untrusted sources.
Audit Metadata