pretext-brainstormer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill codifies social engineering techniques to generate phishing pretexts for payload delivery and credential capture. This framework could potentially be used to circumvent safety guardrails regarding the generation of deceptive content.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external research sources during its research phase. Ingestion points: External news, blog posts, and operational notices researched in SKILL.md Step 1. Boundary markers: The instructions lack delimiters or explicit warnings to ignore instructions embedded within the researched content. Capability inventory: The skill is limited to text generation for pretexts and rankings. Sanitization: No sanitization of external content is specified.
Audit Metadata