skill-creator

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The scripts/init_skill.py utility generates a boilerplate Python script (scripts/example.py) based on a static template and grants it execution permissions (chmod 0o755). This behavior is consistent with its primary function as a project scaffolding tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that involves ingesting user-provided examples and external documentation stored in the references/ directory, which creates a potential surface for indirect prompt injection.\n
  • Ingestion points: User input for skill functionality and content from files within the references/ and assets/ directories as described in SKILL.md.\n
  • Boundary markers: None explicitly required in the template, though the skill provides a structured format for instructions.\n
  • Capability inventory: File system operations (read/write) and command execution for validation and packaging are present in scripts/init_skill.py and scripts/package_skill.py.\n
  • Sanitization: scripts/quick_validate.py performs basic validation of skill metadata, including length checks and character restrictions for descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:53 PM