lead-channel-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of business performance metrics (leads per month, cost per lead, close rate, revenue). An attacker who can influence these metrics could potentially embed instructions within the channel names or descriptions to influence the agent's behavior during the analysis phase.
- Ingestion points: Untrusted data enters the context in
SKILL.mdduring 'Step 1: Channel Inventory' and 'Step 3: Honest Assessment' where the user provides channel lists and performance details. - Boundary markers: The skill lacks explicit instructions or markers to ignore potentially malicious instructions embedded within the user-provided data.
- Capability inventory: The skill primarily performs calculations and generates structured text reports. It does not appear to use subprocess calls, network operations, or file-writing capabilities in its provided scripts.
- Sanitization: There is no evidence of sanitization or validation of the input data to filter out potential command or prompt injections.
Audit Metadata