mobile-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted third-party mobile application codebases, creating a potential surface for indirect prompt injection if malicious instructions are embedded within the source files.
- Ingestion points: The mobile application source code and configuration files read during Phase 1 through Phase 8 as specified in
SKILL.md. - Boundary markers: Absent. The instructions do not employ any delimiters or specific guardrails telling the agent to ignore natural language instructions encountered within the source code.
- Capability inventory: File system read operations across the target project directories and conditional file write operations to
~/.claude/projects/for logging execution telemetry. - Sanitization: Absent. There is no evidence of filtering, escaping, or schema validation applied to the codebase content before it is integrated into the agent's context.
Audit Metadata