grc-portfolio-planner

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a find command within the user's ~/.claude directory to locate the plugin's own scripts and establish a root path (PLUGIN_ROOT).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: User responses to the conversational questionnaire in Steps 1 through 5, including professional summaries and accomplishment descriptions.
  • Boundary markers: Absent. The skill does not provide instructions to the agent to delimit or escape the user-provided text when generating files.
  • Capability inventory: The skill uses tools including Bash, Read, Write, Edit, and Glob to generate and manage files.
  • Sanitization: Absent. User-provided strings are interpolated directly into site-config.json and SITE-PLAN.md without filtering or validation.
  • [DATA_EXFILTRATION]: The skill collects potentially sensitive information from the user, including PII (email, location) and AWS configuration details (SES verified identities, AWS CLI profile names), to store in local configuration files. While this is intended for project setup, it involves handling sensitive configuration data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:27 PM
Security Audit — agent-trust-hub — grc-portfolio-planner