Skills
Navigate
skills/daveebbelaar/bama/build-and-verify/Gen Agent Trust Hub

build-and-verify

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to execute several shell scripts within the project directory, including ./build.sh, tools/snap.sh, tools/grid-lint.sh, and tools/selftest.sh. It also allows executing system commands like xcodebuild, swift, and screencapture for app verification.
  • [DYNAMIC_EXECUTION]: The agent runs local Swift scripts (tools/check-layout.swift) and compiled app binaries to perform UI snapshots and validation checks.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and act upon the output of build and test scripts.
  • Ingestion points: Build logs, stdout/stderr from tools/snap.sh, tools/grid-lint.sh, and tools/selftest.sh.
  • Boundary markers: No explicit markers used to separate external tool output from agent instructions.
  • Capability inventory: Shell command execution via Bash tool and file reading via Read tool.
  • Sanitization: None; the agent is expected to interpret raw tool output for decision making.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:23 PM