bro-init-memory-bank

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run a local shell script, scripts/init-memory-bank.sh, to create the necessary directory structure and copy template files. This is a standard initialization procedure using local files provided within the skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes repository files such as READMEs and configuration files to populate project documentation.
  • Ingestion points: Project repository files including README, package-files, and CI-configs as specified in workflows/init-memory-bank.md.
  • Boundary markers: Absent; the instructions do not define specific delimiters or warnings to ignore instructions within the ingested files.
  • Capability inventory: The skill is capable of executing shell scripts and performing file system writes.
  • Sanitization: Absent; there is no mention of filtering or validating the content extracted from the repository files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 03:46 AM
Security Audit — agent-trust-hub — bro-init-memory-bank