The Agent Skills Directory

Prompt Injection (SAFE): The instructions are strictly task-oriented, focusing on mechanical migration rules. No attempts to bypass safety filters or extract system prompts were detected.\n- Data Exfiltration (SAFE): No network operations or hardcoded credentials were found. The skill does not access sensitive system files like SSH keys or environment configs.\n- Obfuscation (SAFE): All content is in plain text. No encoded strings, zero-width characters, or homoglyphs were detected.\n- Remote Code Execution (SAFE): No external downloads or piped remote execution patterns (e.g., curl|bash) were found. All operations are local.\n- Command Execution (SAFE): The included shell scripts (find-bd-refs.sh, verify-migration.sh) use standard, safe utilities like grep and sed for file validation and do not execute untrusted input.\n- Indirect Prompt Injection (SAFE): While the skill processes user-provided markdown files, the risk is mitigated by the deterministic nature of the transforms and the specific scope of the migration task. Mandatory Evidence Chain: 1) Ingestion points: User-provided markdown files (e.g., AGENTS.md). 2) Boundary markers: Absent. 3) Capability inventory: Read, Edit, and Bash access for local validation. 4) Sanitization: None. Severity dropped to SAFE as the surface is inherent to the primary migration purpose.

bd-to-br-migration