changelog
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary user input via the
$ARGUMENTSvariable and passes it directly to thewrite-changelogskill. This establishes a data flow from an untrusted source to a functional capability without any boundary markers or validation. - Ingestion points:
$ARGUMENTSvariable inSKILL.md. - Boundary markers: Absent; the skill does not wrap input in delimiters or provide safety instructions to the downstream tool.
- Capability inventory: Invocation of the
write-changelogskill using theSkilltool. - Sanitization: Absent; the instructions explicitly mandate passing arguments "unchanged".
Audit Metadata