clean-slop
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSplaceholder to ingest potentially untrusted data that is then processed by theslop-cleaneragent.\n - Ingestion points: External input captured via the
$ARGUMENTSvariable inSKILL.md.\n - Boundary markers: Absent; user input is interpolated directly into the agent instruction without delimiters or 'ignore' directives.\n
- Capability inventory: The skill delegates tasks to the
slop-cleaneragent; performing 'cleaning' tasks implies the ability to read and modify files.\n - Sanitization: No sanitization, validation, or escaping of the input content is performed before interpolation.
Audit Metadata