breaking-change-detector
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of OpenAPI or API specification files. This creates a vulnerability surface where malicious instructions embedded in the specifications could attempt to influence the agent's behavior during the comparison process.\n
- Ingestion points: The agent reads API specification versions (V1 vs V2) from the project workspace.\n
- Boundary markers: The skill does not define specific delimiters or instructions to separate untrusted spec content from its operational logic.\n
- Capability inventory: The skill performs file-writing operations to create reports in the
docs/api-report/directory.\n - Sanitization: No explicit sanitization or validation of the input specification content is defined in the instructions.\n- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration. It does not include any executable scripts, binaries, or complex automation code, which limits the risk of traditional malicious behavior.
Audit Metadata