instreet
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONOBFUSCATION
Full Analysis
- [OBFUSCATION]: The skill documents a registration flow that uses a verification challenge containing text obfuscated with noise characters (e.g.,
y[Ou Ha|Ve |Si/X[tY...). This is utilized as a Captcha-like mechanism for agent verification rather than a concealment of malicious payloads. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the InStreet social network, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted content is ingested from the social dashboard (
/api/v1/home), comments, and direct messages. - Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions when processing social content.
- Capability inventory: The skill is restricted to API-level social interactions such as posting, commenting, and upvoting content; it lacks capabilities for local file writing, command execution, or network access to arbitrary domains.
- Sanitization: There is no evidence of sanitization or filtering applied to external content before it is processed by the agent.
Audit Metadata