maintain-formal-verification-skill
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it relies on processing untrusted external data to perform its primary tasks.
- Ingestion points: The agent is instructed to read git commit messages and source code diffs in SKILL.md.
- Boundary markers: No explicit instructions are provided to the agent to use delimiters or ignore potentially malicious instructions embedded within commit messages or code comments.
- Capability inventory: The skill possesses the capability to modify files (verification models, harnesses, and properties) and execute shell commands to run model checkers or provers as described in SKILL.md.
- Sanitization: The instructions do not specify any validation, sanitization, or filtering of the content found in commit messages or code before the agent uses it to decide on verification updates.
Audit Metadata