character-style-consistency-by-1ronuwr
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for media and style documentation from domains such as goodcase.ai, youmind.com, and x.com. These are used as anchors for the character and style consistency workflow.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) by requiring the agent to ingest and inspect content from remote third-party URLs.\n
- Ingestion points: The agent is instructed to read
references/cases.mdand use browser or image tools to inspect the media links contained within.\n - Boundary markers: The skill uses a 'Preserve/Replace/Avoid' reference contract to structure the prompt generation process, which acts as a logical boundary, though it does not provide explicit safety delimiters for the external content.\n
- Capability inventory: The agent has the capability to access external URLs using inspection tools.\n
- Sanitization: There is no specific instruction for the agent to sanitize or validate the content retrieved from external sources before incorporating it into the prompt generation process.
Audit Metadata