elder-care-ops
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is instructed to 'Scan package manifests', 'Read core schemas', and evaluate actual codebases. If these external files contain malicious instructions, the agent may follow them because there are no boundary markers or instructions to ignore embedded commands in the data being processed.
- Ingestion points: Reads files across the target codebase, including package manifests and schemas.
- Boundary markers: Absent. The skill does not use delimiters or instructions to disregard instructions found within the audited files.
- Capability inventory: Reads files, writes analysis to the
docs/directory, and appends telemetry to~/.claude/projects/. - Sanitization: Absent. Data from the codebase is processed directly into the final report.
- [COMMAND_EXECUTION]: The skill includes a telemetry mechanism that attempts to locate and write to
~/.claude/projects/skill-telemetry.md. While this is intended for performance tracking, it represents an automated file system write to a sensitive configuration directory outside the immediate project scope.
Audit Metadata