privacy-audit
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and analyzes untrusted data from mobile application codebases. Malicious instructions hidden in comments, strings, or metadata within the audited code could potentially influence the agent's behavior.
- Ingestion points: The skill reads codebase content from the path provided in
$ARGUMENTSor the current working directory, specifically targetingAndroidManifest.xml,Info.plist, and source code files for identifier and SDK tracking. - Boundary markers: The instructions lack defined delimiters or clear directives for the agent to separate content being audited from its operational instructions.
- Capability inventory: The skill has access to
Read,Glob,Grep,Bash, andTasktools, allowing for file system traversal and command execution. - Sanitization: No sanitization, filtering, or validation of the ingested codebase content is described in the audit procedure.
Audit Metadata