tam-building
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from LinkedIn Sales Navigator, which is an external and potentially untrusted source.
- Ingestion points: Data enters the agent's context through the
salesnav_companiesmodel inmodels/salesnav-companies.tsusing thefetchAccountSearchaction. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the fetched LinkedIn company data.
- Capability inventory: The skill has the capability to perform database operations (
model.upsert) and call external business matching/enrichment APIs via thecargoDbconnector. - Sanitization: The
promoteCompanyworkflow inplays/promote-to-accounts.tsimplements basic validation using Zod for input structure and checks for the presence of a website before promotion. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of external vendor packages and resources.
- Evidence: The
SKILL.mdfile specifies the installation of the@cargo-ai/clipackage and references fetching thedeploy-cookbookfrom the officialgetcargohqGitHub repository. - [COMMAND_EXECUTION]: The documentation includes multiple examples of shell commands for the user to execute using the
cargo-aiCLI tool. - Evidence: Instructions in
README.mdandSKILL.mdguide the user to runcargo-ai orchestration action executeto count searches andnpx skills addto scaffold the environment.
Audit Metadata