The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to perform project analysis. It executes node to parse the project's package.json file and extract relevant dependency versions (such as Capacitor plugins, authentication, and analytics SDKs). It also uses find to identify critical Apple-specific configuration files including Info.plist, *.entitlements, and PrivacyInfo.xcprivacy. These operations are limited to the local file system and are directly relevant to the skill's primary function.
[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill's behavior is consistent with its stated purpose of assisting with App Store compliance. References to external tools like the asc (App Store Connect) CLI are standard for the intended workflow.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from untrusted project files:
Ingestion points: Reads content from package.json, Info.plist, capacitor.config.*, and local metadata directories.
Boundary markers: The skill does not define explicit delimiters or instructions to prevent the agent from obeying instructions that might be embedded within the project files being audited.
Capability inventory: The skill allows the agent to execute subprocesses (node, find, asc) and read/write local project files.
Sanitization: There is no evidence of content sanitization or validation performed on the data extracted from the project environment before it is analyzed by the agent.

capacitor-apple-review-preflight