salesloft-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from release artifacts, test results, and configuration files using file-system tools. This creates an attack surface where instructions embedded in those data sources could influence the agent's output.
- Ingestion points: Analyzes local files including release artifacts, test logs, runbooks, and configuration files via
Read,Glob, andGreptools. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed data are present.
- Capability inventory: The skill is authorized to use
Read,Glob,Grep,WebFetch,Write, andEdittools. - Sanitization: The skill does not define any validation or sanitization protocols for the content extracted from the analyzed files.
- Risk: A malicious actor with the ability to modify project artifacts (e.g., via a compromised CI/CD pipeline or pull request) could embed instructions designed to trick the agent into issuing a false 'GO' decision or performing unauthorized tool operations.
Audit Metadata