The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard macOS developer tools including leaks, xcrun simctl, and launchctl to inspect process memory and simulator state. These operations are essential to the skill's stated purpose of memory debugging. Evidence: scripts/capture_sim_memgraph.sh uses xcrun simctl to interact with simulators and leaks to generate memgraphs. Evidence: scripts/summarize_memgraph_leaks.py uses subprocess.run with list-based arguments to invoke the leaks utility safely, avoiding shell injection vulnerabilities.
[SAFE]: The skill follows security best practices for local utility scripts. No network operations or external data exfiltration patterns were detected. All external tool invocations use quoted variables or list-based arguments to prevent command injection. Temporary files are handled using mktemp and bundle identifiers are sanitized to prevent path manipulation. The skill also parses memory content from local processes; while this represents a potential ingestion point for untrusted data (Indirect Prompt Injection surface), the risk is mitigated by the use of structured regex parsing and isolating output in markdown code blocks. Ingestion points: scripts/summarize_memgraph_leaks.py reading output from the leaks command; Boundary markers: Excerpts are enclosed in markdown code blocks (~~~text); Capability inventory: Subprocess calls to standard binaries; Sanitization: Regular expression field extraction instead of raw interpolation.

ios-memgraph-leaks