aif-qa
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize content from the repository's codebase and version control history, which could be manipulated by an attacker to influence the agent's behavior or outputs.
- Ingestion points: The skill reads source code files (
Read,Grep,Glob), git diffs and logs (Bash), and project documentation (DESCRIPTION.md,ARCHITECTURE.md). It also reads a mandatory context file.ai-factory/skill-context/aif-qa/SKILL.mdwhich allows for project-level overrides. - Boundary markers: The instructions do not specify any delimiters or safety guidelines for the agent to differentiate between its own instructions and potentially malicious instructions embedded in the analyzed code or documentation.
- Capability inventory: The skill has the capability to write files (
Write), execute a range of git and directory management commands (Bash), and utilize exploration sub-agents (Task). - Sanitization: No sanitization or validation is mentioned for the content retrieved from the codebase, git history, or user-supplied implementation summaries.
Audit Metadata