threads-hook-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted text from Threads posts provided by the user. This creates a surface where malicious instructions embedded within a post could theoretically attempt to manipulate the agent's classification logic or output formatting.
- Ingestion points: In
SKILL.md, the agent is instructed to ask the user to paste the post or thread text for analysis. - Boundary markers: The skill does not currently define specific delimiters (such as XML tags or unique markers) or explicitly instruct the agent to ignore directives that might be present within the source text.
- Capability inventory: The risk is mitigated by the skill's limited capability scope; it focuses on text classification and template generation without performing dangerous operations like file system modification, network requests, or arbitrary code execution.
- Sanitization: There is no evidence of input sanitization or escaping of the user-provided text before it is processed by the model.
Audit Metadata