mathcalcu-video
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses various shell commands and Python module invocations (
python -m mcp_video) for video editing tasks such as merging segments, adding audio, and applying watermarks. These commands are necessary for the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill ingests content from an external source (
MathCalcu_VideoPromo_Script.md), which is a common surface for indirect prompt injection. - Ingestion points:
C:\Users\joashua\Downloads\MathCalcu_VideoPromo_Script.md(SKILL.md) - Boundary markers: None present; the skill does not use specific delimiters or instructions to ignore embedded commands in the source script.
- Capability inventory: The skill has the ability to execute shell commands via the
mcp-videoCLI and perform file operations (copy). - Sanitization: No explicit validation or escaping of the input script's content is described.
Audit Metadata