adjust-abstraction-scope
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML metadata. No executable scripts (.py, .js, .sh), binary files, or tool configurations are included in the skill package.- [SAFE]: Comprehensive analysis found no evidence of malicious behavior, obfuscated content, or attempts to access sensitive system resources.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research objects and scope descriptions, which constitutes an input ingestion surface. However, the lack of any system capabilities renders this surface non-exploitable.
- Ingestion points:
research_objectandcurrent_scopeparameters defined inSKILL.md. - Boundary markers: None provided.
- Capability inventory: The skill has no defined tools, network access, or file system permissions.
- Sanitization: Not implemented, as the skill only performs text-to-text transformation within the agent's context.
Audit Metadata