agent-architecture-audit
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's primary function is to analyze untrusted external data from codebases and logs, presenting a surface for indirect prompt injection.
- Ingestion points: The auditing workflow defined in
SKILL.md(Phase 2: Evidence Collection) directs the agent to read and search through various files in a target application. - Boundary markers: There are no instructions for the agent to use delimiters or specifically ignore embedded prompts when processing the content of these files.
- Capability inventory: The skill is granted extensive capabilities, including
Read,Write,Edit, andBashaccess (listed in theSKILL.mdfrontmatter). - Sanitization: The workflow lacks specific steps for sanitizing or validating the contents of the files before they are ingested into the agent's context.
Audit Metadata