The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands via the asta CLI and standard utilities (mkdir, cp, ls) to manage feedback directories and prepare submissions.
[DATA_EXFILTRATION]: The skill transmits feedback reports and optional supporting files to the vendor's infrastructure using the asta feedback submit command. This behavior is the primary purpose of the skill and is protected by explicit user confirmation and a dry-run manifest review before any network activity occurs.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the ingestion of untrusted project data.
Ingestion points: The skill reads project context via ls and git log (in workflows/interview.md) and incorporates user-provided content into the generated narrative report.
Boundary markers: No specific delimiters or instructions are used to isolate untrusted project metadata or user-provided feedback from the agent's core instructions.
Capability inventory: The agent has the ability to write to the filesystem (Write), modify files (Edit), and perform network uploads via the asta CLI.
Sanitization: There is no evidence of sanitization, validation, or filtering for the external project content before it is processed by the agent.

feedback