power-words
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user-provided copy for transformation without utilizing delimiters or boundary markers.
- Ingestion points: User copy provided via the 'Current copy' instruction in SKILL.md.
- Boundary markers: Absent. No triple-quotes or XML tags are defined to isolate user data.
- Capability inventory: 'Write' and 'Edit' tools are available in SKILL.md, allowing the agent to modify files based on potentially injected instructions.
- Sanitization: Absent. No validation or filtering is specified for the input text.
- [COMMAND_EXECUTION]: The skill uses file system tools ('Read', 'Write', 'Edit', 'Grep', 'Glob') to manage its word library and perform text edits. These permissions are consistent with the skill's stated purpose of enhancing text files.
Audit Metadata