offensive-idor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and YAML metadata describing a security auditing workflow. No executable scripts, network requests, or sensitive data access patterns were identified within the skill files.- [NO_CODE]: The skill does not include any executable code (e.g., Python, JavaScript, Shell), which eliminates the risk of direct malicious code execution or automated system compromise from the skill itself.- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external data, such as REST/GraphQL endpoints and source code, creating a potential surface for indirect prompt injection if those external sources contain malicious instructions.
- Ingestion points: Analyzing REST/GraphQL endpoints, source code, and binary bundles as described in SKILL.md.
- Boundary markers: None identified in the provided instructions to delimit external data from agent instructions.
- Capability inventory: Mentions using search tools (rg), AST analysis, and decompilation for assessment and remediation (SKILL.md).
- Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata