saas-outcomes
Fail
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: CRITICALDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The file
references/experts.mdcontains numerous links to external domains, specificallykeithrosen.comandforgetthefunnel.com, which have been flagged by automated scanners for malware and blacklisting. Directing users or agents to these domains poses a risk of exposure to malicious content. - [COMMAND_EXECUTION]: The skill includes a local Python script
scripts/check-output.py. While the current logic is restricted to validating string patterns in local files, providing scripts within a skill creates a vector for local code execution if the file is modified or if the environment allows execution of arbitrary scripts. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied business data (such as ARR, growth metrics, and founder objectives). It lacks robust boundary markers or safety instructions to prevent the agent from following malicious instructions that could be embedded in the data processed during phase-based assessments.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 8 malicious URL(s) - DO NOT USE
Audit Metadata