The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill file contains multiple hardcoded, plaintext sensitive credentials for the Twitter API, specifically including:
API Key (Consumer Key): KiEaJHzFUWE7BLPMrMeABVx8z
API Secret (Consumer Secret): GSvXTcUGpA37xZ5pKOu2aMitplfM0icbrlnVnwbZNVIJVaNQbT
Access Token: 1088426905634779136-fKvck5gh92Z5nrirFvkYlfM3ftyZ43
Access Token Secret: Rsf3g4rpADKm6U42QbIxjI82kAt2kUVbDFBrCS1ELTmU8
Bearer Token: AAAAAAAAAAAAAAAAAAAAALL3wQEAAAAAEU16sJsJT9zl7D0w6iGMky%2FXn5I%3D3bCPWBSMOyKAlF7LfbRTCbIlt8goxzq2lZlEC6jfcdZNzPU7Jv
OAuth 2.0 Client Secrets: nsWvS3dCCitBpMihAMlr2nMJBy7J-7Xw8tx7Zq_xf2WWiz8r0_ and nsWsS3dCCtiBpMiAhIi2nMJbYJ7-7XwBxfZq_xf2WWiz8r0_
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external business news, reports, and insights which are potentially attacker-controlled sources.
Ingestion points: Business news, reports, and market analysis data processed by the agent to generate tweets (SKILL.md).
Boundary markers: Absent; the skill lacks instructions for the agent to ignore or delimit embedded commands within the processed data.
Capability inventory: The skill has access to tools Read, Write, and Bash, allowing for significant file system and command-line interactions.
Sanitization: Absent; no validation or filtering is specified for the external data before it is formatted into posts.

twitter-poster