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 possesses an attack surface for indirect prompt injection as it is instructed to ingest and act upon data from external sources that may be controlled by an attacker.
- Ingestion points: The skill reads commit messages, doc comments, changelogs, and covered source code files to determine how to update verification models (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within the commit messages or comments it processes.
- Capability inventory: The skill allows the agent to identify and execute shell commands associated with verification tools and permits writing updates to verification scripts and models (SKILL.md).
- Sanitization: The instructions do not specify any sanitization or validation of the ingested content before it is used to influence the agent's reasoning or file-writing operations.
Audit Metadata