doc-to-skill
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external documentation provided by users. It lacks explicit instructions for the agent to use boundary markers or to ignore potential malicious instructions embedded within the source documentation.\n
- Ingestion points: User-supplied source documents analyzed in SKILL.md (Step 1).\n
- Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions within the source text.\n
- Capability inventory: The skill references file initialization and packaging scripts for command-line execution.\n
- Sanitization: No sanitization or validation of the input documentation content is described.\n- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill references and encourages the use of local Python scripts for core tasks like initialization and packaging that are not part of the skill package.\n
- Evidence: SKILL.md mentions
python init_skill.py <skill-name>,python package_skill.py <path/to/skill>, andpython quick_validate.py <path/to/SKILL.md>.\n - Unverifiable Dependencies: These scripts are not included in the provided file set, meaning their source, integrity, and behavior cannot be verified, creating a dependency on external code of unknown provenance.
Audit Metadata