comedy-style-skill-generator
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data when a requester provides a comedic tradition, performer name, or example bits for analysis (Workflow Step 2 in SKILL.md). There are no explicit boundary markers or instructions to ignore embedded commands within these inputs. The capability inventory is restricted to text analysis and generation of a markdown file, with no access to external network tools or file system writing. No sanitization or validation of the input content is implemented.\n- [SAFE]: No other malicious patterns, including obfuscation, unauthorized data access, or privilege escalation, were detected in the skill instructions or supporting evaluation files.
Audit Metadata