vertex-ai-media-master

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected.
  • Ingestion points: External media files (videos, images, audio) and text briefs are ingested for analysis and generation across multiple files, including SKILL.md and references/examples.md (e.g., via model.generate_content).
  • Boundary markers: Analysis of references/examples.md reveals that prompts provided to the models do not include delimiters or instructions to ignore embedded commands within the processed media.
  • Capability inventory: The skill operates in an environment with broad tool permissions including Bash(general:*), Bash(util:*), Write, Edit, and Read, as specified in the allowed-tools frontmatter of SKILL.md.
  • Sanitization: There is no evidence of input sanitization or filtering for instructions hidden within media metadata, transcriptions, or visual text overlays.
  • [COMMAND_EXECUTION]: While the skill defines Bash tools in its allowed-tools configuration to scope access, the combination of shell access with the processing of untrusted external content increases the potential impact of an indirect prompt injection attack.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:53 PM