video-script
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its research workflow.\n
- Ingestion points: The skill uses
WebFetchto read reference articles from arbitrary URLs andRead/Grep/Globto explore local code repositories provided by the user (Step 2 of the workflow).\n - Boundary markers: There are no explicit delimiters or system instructions provided to the agent to ignore or isolate potential malicious instructions embedded within the fetched external content.\n
- Capability inventory: The agent has permissions to create directories and write files to the local file system (Step 3, 4, 5, 6) and can perform network operations via
WebSearchandWebFetch.\n - Sanitization: There is no evidence of content sanitization, escaping, or validation of the data retrieved from external sources before it is interpolated into the script generation prompts.
Audit Metadata