dx-devops-request-status

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a focused, read-only utility for polling Salesforce DevOps Center request statuses. It does not perform mutations or access sensitive local files.
  • [COMMAND_EXECUTION]: The skill utilizes a shell script (scripts/poll-status.sh) to execute sf devops request status and jq. The implementation follows security best practices by passing user-supplied values (tokens and org aliases) as CLI flags and using proper shell quoting, which mitigates command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as request tokens and org aliases. 1. Ingestion points: The REQUEST_TOKEN and TARGET_ORG parameters enter the agent context via CLI arguments in SKILL.md. 2. Boundary markers: No explicit prompt delimiters are used for the token, but the skill body contains critical instructions forbidding shell string interpolation. 3. Capability inventory: Subprocess execution of the sf CLI for network-based status checks (scripts/poll-status.sh). 4. Sanitization: The shell script uses double-quoting for variables and printf to pass data safely to jq filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:04 AM
Security Audit — agent-trust-hub — dx-devops-request-status