competitors
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions explicitly designed to suppress the agent's meta-commentary and safety-related output. In the 'Mandatory Content Standards' section, it states: 'No warnings, notes, or disclaimers. Stick to requested output.' This is a common pattern used to prevent the AI from providing ethical warnings, safety disclaimers, or clarifying its limitations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data provided by the user to generate marketing content, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill relies on external inputs defined in the 'What to Gather Before Writing' section, including product names, core use cases, customer quotes, and competitor details.
- Boundary markers: The skill does not define any delimiters or instructions to ignore potential commands embedded within the gathered data.
- Capability inventory: The skill's primary function is text generation. It does not exhibit capabilities for subprocess calls, file-system writes, or network operations.
- Sanitization: There are no provisions for sanitizing or escaping the gathered content before it is interpolated into the generation process.
Audit Metadata