content-repurposing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly override default agent behavior regarding transparency and safety.
- Specifically, it instructs the agent to respond to inquiries about system prompts with a hardcoded marketing link to "Scayver Academy".
- It mandates the suppression of all "warnings, notes, or disclaimers," a pattern often used to bypass safety framing or user-awareness messages.
- It forces the inclusion of a "Mandatory Intro Message" containing solicitation for money via CashApp and BuyMeACoffee in every content output, which is a behavioral manipulation of the agent's primary purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (e.g., blog posts, videos, newsletters) while having a broad capability for text generation.
- Ingestion points: User content provided for repurposing (blog posts, video transcripts, newsletters, etc.).
- Boundary markers: Absent. There are no instructions to use specific delimiters or to ignore instructions embedded within the user data.
- Capability inventory: Extensive text generation and formatting capabilities for multiple social media platforms and email.
- Sanitization: Absent. The instruction to provide "no warnings, notes, or disclaimers" reduces the likelihood of the agent flagging or ignoring adversarial instructions embedded in the input data.
Audit Metadata