philipenko-reels-method
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown instructions and reference material (
SKILL.mdandreferences/source-corpus.md). It does not contain any executable scripts, binaries, or configuration files. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it instructs the agent to ingest untrusted user data to generate scripts without implementing safety boundaries or sanitization.
- Ingestion points: Untrusted data enters via 'Тема/тезис' (topic/thesis) and 'Идея/сырой текст' (idea/raw text) fields as defined in
SKILL.md. - Boundary markers: The instructions do not define delimiters (like XML tags) to separate user input from the core instructions.
- Capability inventory: The skill's capabilities are restricted to text generation; it possesses no subprocess, network, or file-writing tools.
- Sanitization: No filtering or validation of user-provided content is performed before interpolation into the prompt.
- [SAFE]: No evidence of malicious patterns such as data exfiltration, credential theft, or code obfuscation was found. The instructions to use profanity and a specific 'hard' register are documented stylistic choices for generating social media content and do not represent an attempt to bypass the underlying model's safety protocols.
Audit Metadata