modernize
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including pull request titles, descriptions, linked issues, and review threads to determine the 'intent' of the work. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions within these fields to manipulate the agent's behavior during the modernization process.
- Ingestion points: Pull request title, body, linked issues, commits, and review threads (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading external PR content.
- Capability inventory: The skill possesses credentials to interact with git repositories and perform write operations such as
git push --force-with-lease(SKILL.md). - Sanitization: There are no programmed steps to sanitize or filter potential instructions from the ingested PR metadata.
Audit Metadata