asd-ste100-zh
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-supplied technical text. While it lacks explicit XML-style boundary markers for the input data, the agent's instructions are strictly limited to structural rewriting and linguistic analysis, reducing the risk of malicious instructions within the data affecting the agent's core behavior.
- [COMMAND_EXECUTION]: The skill includes a local utility script,
scripts/ste-lint.py, which the agent is instructed to run for structural analysis of English text. Analysis of the script confirms it uses only Python standard libraries (re, json, sys, etc.) and performs string-based heuristic checks. It does not contain network access, file system modification (beyond reading inputs), or other dangerous capabilities. - [EXTERNAL_DOWNLOADS]: The README provides installation instructions using the
npx skills addcommand pointing to the author's own repository (github.com/lltx/skills). As this is the official installation method for the skill itself and originates from the skill's author, it represents intended functionality.
Audit Metadata