wendy-security-baselines
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to review and write code based on specific security baselines. This role requires processing untrusted external inputs such as pull request diffs and new code contributions, which constitutes an attack surface for indirect prompt injection. Malicious instructions could potentially be embedded within the code or comments under review to influence the agent's behavior.
- Ingestion points: The skill is intended to be used when reviewing or writing code touching interop components like pki-core, wendy-auth, and wendy-proxy as specified in SKILL.md.
- Boundary markers: The skill does not specify the use of delimiters or explicit instructions for the agent to ignore potentially adversarial commands contained within the reviewed data.
- Capability inventory: The agent is tasked with high-level code analysis, architectural verification, and generating code changes based on the AAA contract.
- Sanitization: There are no specific requirements or procedures provided for sanitizing or escaping the content of external code before the agent processes it.
- [NO_CODE]: The skill consists entirely of markdown documentation and reference files. It does not include any executable scripts, binaries, or automated shell commands.
Audit Metadata