asd-ste100-skill
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The README.md file includes installation instructions that download the skill from the author's GitHub repository (
github.com/TwiTech-LAB/devchain). These downloads use standard developer tools (degit,curl) and target well-known, established infrastructure belonging to the skill author. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite arbitrary text provided by users or other agents, which represents an indirect prompt injection surface.
- Ingestion points: The skill accepts English text for rewriting as specified in
SKILL.md. - Boundary markers: There are no explicit delimiters defined for input data in the prompt instructions, although the instructions require the agent to output only the transformed text.
- Capability inventory: The skill possesses no high-risk capabilities; it does not have access to file-writing tools, network operations, or shell execution.
- Sanitization: No specific sanitization or filtering of input text is defined, but the lack of exploitable tools mitigates this risk.
- [NO_CODE]: This skill is entirely instructional and does not include any Python scripts, JavaScript files, or binary executables. It functions solely through natural language instructions within the agent's environment.
Audit Metadata