call-summary
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to process external, potentially untrusted text from call transcripts and notes. This creates a surface where instructions embedded in the analyzed data could attempt to influence the agent's behavior.
- Ingestion points: The skill accepts input via the
$ARGUMENTSvariable and referenced files (@$1) as seen inSKILL.md. - Boundary markers: The instructions do not currently define explicit delimiters or 'ignore' commands to help the agent distinguish between the transcript content and the skill's operational instructions.
- Capability inventory: The skill mentions capabilities to update CRM records, create tasks, and draft or send emails if external connectors are enabled, according to the
SKILL.mdfile. - Sanitization: There are no explicit sanitization or validation steps defined in the instructions to filter the input content before processing.
Audit Metadata