craft-experiment-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the
$ARGUMENTSvariable within the<context>tag. While this creates a surface where a user could attempt to override instructions, the skill possesses no sensitive capabilities such as network access, file system manipulation, or command execution. \n - Ingestion points: SKILL.md via
$ARGUMENTS\n - Boundary markers:
<context>tags are used to delimit user input\n - Capability inventory: None. No tool calls or scripts are defined\n
- Sanitization: None\n- [NO_CODE]: The skill consists entirely of markdown instructions and prompt templates without any accompanying scripts, binaries, or package dependencies.
Audit Metadata