status

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script to generate its status report.
  • Evidence: python ${CLAUDE_PLUGIN_ROOT}/scripts/dm-status.py [--brand <slug>] [--json] [--quiet] [--section <name>] is called in SKILL.md.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external brand and engagement data.
  • Ingestion points: Reads and parses data from files in ~/.claude-marketing/brands/ and ${CLAUDE_PLUGIN_DATA}/digital-marketing-pro/.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its own logic and data content embedded within the ingested JSON files.
  • Capability inventory: The skill has access to the Bash tool for command execution, creating a potential path for exploitation if malicious instructions are successfully injected via the data files.
  • Sanitization: No validation or sanitization steps are defined for the content extracted from the brand profiles or engagement history.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:24 AM
Security Audit — agent-trust-hub — status