ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a documentation utility that processes conversation text to extract domain concepts. It does not access sensitive files or perform network activity.
- [SAFE]: File system interaction is limited to reading from and writing to 'UBIQUITOUS_LANGUAGE.md' in the local directory, which is essential for the skill's stated purpose of maintaining a persistent glossary.
- [PROMPT_INJECTION]: The skill processes untrusted user input from conversations and reads from a local file, creating an indirect prompt injection surface. However, the risk is negligible as the skill lacks sensitive capabilities such as network access or shell command execution. Evidence Chain: 1. Ingestion points: Current conversation and 'UBIQUITOUS_LANGUAGE.md' (SKILL.md). 2. Boundary markers: None specified in instructions. 3. Capability inventory: File write to 'UBIQUITOUS_LANGUAGE.md' (SKILL.md). 4. Sanitization: No explicit instructions for sanitizing or escaping ingested content.
- [NO_CODE]: No external scripts or executables are included with this skill; it consists entirely of natural language instructions in the SKILL.md file.
Audit Metadata