The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill introduces a vulnerability surface by ingesting untrusted data from an external source (Argos platform comments).
Ingestion points: The skill uses the argos media comment list command (referenced in SKILL.md) to read comments and feedback pinned to screenshots by humans.
Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between the human's feedback and potential malicious instructions embedded within those comments.
Capability inventory: The agent has the ability to execute various shell commands via the argos CLI, including uploading files, updating media metadata, and posting replies or resolving threads.
Sanitization: The skill does not describe any sanitization or validation of the comment text before it is presented to the agent's context.
[COMMAND_EXECUTION]: The skill's primary function is to execute the argos CLI tool. This involves reading local image/video files and performing network operations to communicate with the vendor's infrastructure (argos-ci.com and media.argos-ci.com). These operations are consistent with the skill's stated purpose of uploading media and managing visual reviews.

argos-upload