explain
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXPOSURE_EXFILTRATION]: The skill reads the local
~/.claude/PROFILE.mdfile to personalize its output based on user preferences. This file access is explicitly limited to the profile configuration in the skill's execution scope. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase, web documentation, and screenshots which could potentially contain malicious instructions.
- Ingestion points: Local codebase files (via
Read), external library documentation (viaWebFetch), and user-provided screenshots. - Boundary markers: Absent; the instructions do not include specific delimiters or directives to ignore instructions embedded within the codebase or fetched documentation.
- Capability inventory: The skill utilizes
WebSearch,WebFetch, and file systemReadoperations. - Sanitization: No explicit sanitization or validation of the ingested content is defined within the playbooks.
Audit Metadata