kafka-perspective
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The repository contains no executable code, scripts, or binaries. The functionality is defined entirely through Markdown instructions and reference text files.\n- [NO_CODE]: There are no software dependencies or build scripts that execute during runtime. The installation instructions provided in the README are for the user to manually add the skill to their environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it ingests and processes arbitrary user input to generate persona-based analysis.\n
- Ingestion points: User input strings processed by the agent in SKILL.md.\n
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded in user queries.\n
- Capability inventory: The skill is limited to reading local files (research.md and demo-conversation.md). It does not utilize network access, shell execution, or file writing tools.\n
- Sanitization: Absent; no validation or escaping of user-provided text is specified in the prompt logic.
Audit Metadata