eli5
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data via the $ARGUMENTS placeholder without explicit boundary markers or sanitization, creating a surface for embedded instructions to influence agent behavior.
- Ingestion points: User input provided to the /eli5 command is interpolated into the prompt in SKILL.md.
- Boundary markers: Absent. The input is appended directly to the instructions without delimiters.
- Capability inventory: No high-privilege tools, script execution, or network capabilities are defined.
- Sanitization: No input validation or filtering of the user-supplied topic is present.
Audit Metadata