seo-images
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill uses
WebFetchto retrieve content from user-provided URLs for image analysis inSKILL.md. - Boundary markers: There are no instructions defining delimiters or explicit warnings for the agent to ignore potentially malicious instructions embedded within the fetched HTML, such as those hidden in image alt text or metadata.
- Capability inventory: The skill is configured to allow access to
Bash,WebFetch,Read,Grep, andGlobas seen in the YAML frontmatter. This combination of tools allows for significant file system and network interaction if the agent is manipulated by external content. - Sanitization: The instructions do not specify any sanitization, escaping, or filtering of the content retrieved from the external URLs before the agent processes it.
Audit Metadata