ape-teach
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content from URLs and local files, which presents a surface for indirect prompt injection if the source material contains malicious instructions.
- Ingestion points: The 'Input Handling' section of SKILL.md allows the agent to read from user-provided URLs and local file paths (.md, .txt, .pdf).
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to isolate the ingested data or to ignore instructions contained within those files.
- Capability inventory: The skill uses web research tools and file-reading capabilities to perform its task.
- Sanitization: The instructions do not mandate specific sanitization or validation of the content retrieved from external sources before it is processed.
- [NO_CODE]: The skill is composed entirely of natural language instructions and markdown configuration. It does not include any executable scripts, binaries, or automated environment setup commands, which significantly limits its potential for direct technical exploitation.
Audit Metadata