mobilebuildmcp-docs-command-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from changelogs and manifests, creating an attack surface where malicious instructions embedded in those files could attempt to influence agent behavior.
- Ingestion points:
CHANGELOG.md,manifests/tools/*.yaml,manifests/workflows/*.yaml, andsrc/cli/**accessed via theRead,Grep, andGlobtools. - Boundary markers: The instructions lack explicit delimiters or instructions to the agent to disregard commands or instructions found within the data being reviewed.
- Capability inventory: The skill is restricted to read-only tools (
Read,Grep,Glob), which prevents destructive actions, file modifications, or network exfiltration even if an injection were successful. - Sanitization: No sanitization or validation of the input text is performed before it is added to the agent's context.
Audit Metadata