competitor-intel

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses native CLI tools including motion, slack, and reminder for its core logic. It also includes a shell script (migration-helper.sh) that is made executable during installation to manage local file system organization within the brain directory.
  • [EXTERNAL_DOWNLOADS]: External ad data and brand context are retrieved from the Motion ad library using the motion CLI tool.
  • [DATA_EXFILTRATION]: The skill transmits competitive intelligence reports to an external Slack channel via the slack CLI. This is a primary function requested by the user.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) due to its processing of external competitor ad content.
  • Ingestion points: Ad copy and hook text are fetched from competitor portfolios in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompts handling external content.
  • Capability inventory: The skill possesses the ability to write to files in the brain directory and communicate externally through Slack.
  • Sanitization: External ad content is extracted and quoted verbatim without explicit sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:41 AM
Security Audit — agent-trust-hub — competitor-intel