stakeholder-update
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes raw content from the
$ARGUMENTSvariable within a<context>block to generate a report. - Ingestion points: Raw text context is ingested in
SKILL.mdvia$ARGUMENTSand several user-input placeholders. - Boundary markers: The skill uses
<context>XML-style tags to delimit the input data. - Capability inventory: The skill has no active capabilities; it does not invoke tools, execute shell commands, perform network operations, or write to the file system.
- Sanitization: No explicit sanitization is performed, but the lack of executable capabilities mitigates the risk of injection exploitation.
Audit Metadata