image
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes example shell commands for image optimization using common utilities such as
cwebp,mogrify, andjpegoptim. It also provides acurlcommand designed to extract image source tags from a website for auditing purposes. - [EXTERNAL_DOWNLOADS]: The skill references and provides links to several well-known and reputable AI image generation platforms and APIs, including Google Gemini, OpenAI, Black Forest Labs (Flux), and Ideogram. These references are essential for the skill's stated purpose of helping users create marketing assets.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting untrusted local data.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to read context from files such as.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within these context files are present.
- Capability inventory: The skill facilitates the execution of shell commands (
curl,cwebp,mogrify,jpegoptim) and interacts with external model APIs. - Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from these context files.
Audit Metadata