openapi-spec-generator
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves ingesting and parsing untrusted source code provided by users (e.g., Express, FastAPI, Spring, Django) to automatically extract API endpoints and schemas. This creates a surface for indirect prompt injection attacks where an attacker could embed malicious instructions in code comments, strings, or documentation that the agent might inadvertently follow during the extraction process.
- Ingestion points: Workflow Step 1 and the 'Extracting from Code' section specifically instruct the agent to process user-provided code files.
- Boundary markers: Absent. The instructions do not specify the use of XML-style tags, delimiters, or 'ignore embedded instructions' warnings when processing the untrusted code snippets.
- Capability inventory: Based on the provided SKILL.md, the skill only generates text output (YAML/JSON specifications) and does not utilize tools for file writing, network operations, or shell execution.
- Sanitization: Absent. There are no instructions for the agent to sanitize, escape, or filter the content extracted from user code before incorporating it into the final prompt or output.
- [NO_CODE]: The skill is composed entirely of markdown instructions and configuration metadata. It does not include any executable scripts (.py, .js, .sh), binaries, or automated tool configurations, which significantly limits the risk of direct remote code execution or privilege escalation.
Audit Metadata