The Agent Skills Directory

[SAFE]: The skill implements a structured auditing process for iOS storage locations and persistence channels. It uses tools like Glob, Grep, and Read to inspect project files for known anti-patterns such as improper tmp/ directory usage or missing backup exclusions. \n- [SAFE]: No malicious capabilities were identified. The skill does not request network access, perform file writes, or attempt to execute shell commands. All operations are read-only and restricted to the project's source code. \n- [SAFE]: The instructions do not contain prompt injection or attempts to override safety filters. The directives focus on ensuring the agent uses its scanning tools to provide factual audit results rather than speculating from training data. \n- [SAFE]: There is no evidence of obfuscation, hidden content, or dynamic context injection. The logic is transparently defined in markdown and YAML metadata.

axiom-audit-storage