tweet-thread
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONINGNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user-supplied text to create tweet threads, which creates a surface for indirect prompt injection attacks where malicious instructions could be embedded in the input data. 1. Ingestion points: User-provided context and narrative requests in SKILL.md. 2. Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the input text. 3. Capability inventory: The skill is limited to text generation and does not utilize any tools, network access, or file system operations across all scripts. 4. Sanitization: There are no instructions for sanitizing or validating the contents of the user-provided data before processing.
- [METADATA_POISONING]: The author is identified as "Claude Code" in the frontmatter, which contradicts the actual author "inbharatai". This inconsistency is misleading regarding the skill origin.
- [NO_CODE]: The skill consists entirely of natural language instructions and examples, with no executable scripts or external software dependencies.
Audit Metadata