rename-process

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from the local file system and external repository configurations, creating a surface for indirect prompt injection.
  • Ingestion points: The agent reads directory structures, Git remote configurations, and live tool state from bb-cli as specified in SKILL.md and references/bb-cutover.md.
  • Boundary markers: The instructions do not define explicit delimiters (e.g., XML tags or unique markers) to isolate tool outputs from the agent's core instructions, increasing the risk of the agent following instructions embedded in repository data.
  • Capability inventory: The skill has the capability to perform directory renames, update Git remotes, and modify service configurations or databases via bb-cli.
  • Sanitization: No specific validation or sanitization steps are provided to ensure that data read from external sources (such as Git branch names or remote URLs) is safe before it is used to formulate subsequent shell commands or migration steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:46 PM
Security Audit — agent-trust-hub — rename-process