bevy-help
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from local project files and documentation caches, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill reads
Cargo.toml,Cargo.lock, and various documentation files within${BEVY_HELP_SKILL_DIR}/docs/.\n - Boundary markers: Absent. The instructions do not define delimiters or specific 'ignore' directives for processed file content.\n
- Capability inventory: The skill performs file reading across the project and documentation directories and maintains a persistent log by writing to
./.bevy-help.log.\n - Sanitization: Absent. There is no requirement for the agent to sanitize or validate the content of the files it reads before using them to generate responses.
Audit Metadata