eos-composition
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text for composition review but lacks boundary markers or instructions to ignore commands within the analyzed content.
- Ingestion points: The
$ARGUMENTSplaceholder at the end ofSKILL.mdappends user-provided text to the prompt. - Boundary markers: Absent. There are no delimiters or "ignore embedded instructions" warnings separating instructions from the data to be reviewed.
- Capability inventory: The skill does not invoke any tools, network operations, or file-system write capabilities.
- Sanitization: Absent. User input is appended to the instruction set without filtering or escaping.
Audit Metadata