giggle-generation-video
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at 'scripts/generation_api.py' to interact with the video generation API. This is the primary intended mechanism for the skill.
- [EXTERNAL_DOWNLOADS]: The skill connects to 'https://giggle.pro' to submit video generation tasks and query for results. This network activity is consistent with the skill's stated purpose and targets the vendor's own infrastructure.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted user data in shell commands. 1. Ingestion points: The '--prompt', '--start-frame', and '--end-frame' arguments in 'SKILL.md' ingest user-supplied content. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate or escape these inputs. 3. Capability inventory: The skill performs shell execution via 'python3' and makes network requests via 'requests'. 4. Sanitization: No sanitization or validation logic for the input arguments is specified in the skill's instructions.
Audit Metadata