The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instructions, jailbreak attempts, or system prompt extraction patterns were detected within the skill's instructions.
[DATA_EXFILTRATION]: The skill fetches public data from official app stores and reads local product marketing context files to provide better audit results. It does not attempt to access sensitive system files (like SSH keys or AWS credentials) or exfiltrate data to unauthorized third-party domains.
[REMOTE_CODE_EXECUTION]: There are no commands or patterns associated with downloading and executing remote scripts (e.g., curl|bash).
[OBFUSCATION]: All instructions and reference files are written in clear, plain text. No Base64, zero-width characters, or hidden URLs were found.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from App Store and Google Play listing pages. While these sources are technically external, the skill's primary function is analysis and report generation, which carries a negligible risk of malicious instruction execution compared to skills with more powerful capabilities (like code execution or file system modification).

aso-audit