competitor-tracking

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources such as GitHub issues, community forums, and social media mentions.\n
  • Ingestion points: External data is retrieved via GitHub CLI searches and social listening tool outputs as described in SKILL.md.\n
  • Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the external content.\n
  • Capability inventory: The skill uses the gh command-line tool and involves generating battlecard documents based on the collected data.\n
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from these external sources.\n- [COMMAND_EXECUTION]: The skill provides example commands for the GitHub CLI (gh) to automate data collection from repositories and issue searches. These are standard developer tools and used here for legitimate analytical purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 09:36 AM
Security Audit — agent-trust-hub — competitor-tracking