stop-slop
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted text artifacts (documentation, READMEs, PR messages), which serves as an ingestion point for indirect prompt injection.
- Ingestion points: Described in SKILL.md as durable prose artifacts including docs, READMEs, and issue text.
- Boundary markers: SKILL.md includes a specific instruction to 'Preserve code, commands, data, tables, and quoted third-party material,' which helps prevent the agent from misinterpreting instructions embedded in those sections.
- Capability inventory: No dangerous capabilities such as network access, file system modifications, or subprocess execution are defined in the provided skill scripts or configuration.
- Sanitization: No specific input sanitization or filtering logic is implemented beyond the preservation instructions.
Audit Metadata