edit-assist
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external files that may contain untrusted instructions.
- Ingestion points: Accesses project-level references via
../../references/EDIT_ASSIST.mdand processes external subtitle/transcript text. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within these external files.
- Capability inventory: The skill is capable of executing a local script
scripts/edit_assist.pyfor media processing. - Sanitization: No evidence of sanitization or validation of the external reference content is provided in the skill instructions.
- [COMMAND_EXECUTION]: The skill performs its primary function by executing a local script at
scripts/edit_assist.py, which is a standard pattern for deterministic agent tools.
Audit Metadata