audit-project
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests and processes content from a project's source tree and configuration files.
- Ingestion points: The agent is instructed to read
pom.xml,application.properties, and thesrc/main/javadirectory (Step 4.1 in SKILL.md). - Boundary markers: The instructions do not provide explicit delimiters or warnings for the agent to ignore instructions embedded within the files being audited.
- Capability inventory: The skill utilizes the
quarkus-agentandcontext7MCP tools to perform status checks, documentation searches, and pattern validation. - Sanitization: No sanitization or content filtering is specified for the project files before they are processed in the audit.
Audit Metadata