The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell scripts and system utilities to interact with external APIs and manage local configuration files.
Evidence: SKILL.md provides bash templates for executing API calls; scripts/dt_helper.sh uses curl for network requests and sed for updating the configuration file.
[DATA_EXFILTRATION]: The skill is designed to access and display sensitive organizational data, including employee names, phone numbers, and job titles.
Evidence: references/api.md documents endpoints that return full user details, including sensitive fields like mobile and email.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from DingTalk's directory (such as names and titles) that could potentially contain malicious instructions if the source data is compromised or controlled by an adversary.
Ingestion points: Data ingested from DingTalk API responses via curl (e.g., SEARCH and DETAIL variables in SKILL.md template).
Boundary markers: None identified; the skill processes the retrieved JSON data without explicit delimiters to isolate it from the agent's core instructions.
Capability inventory: The skill has the ability to execute shell commands, perform network operations, and modify local configuration files.
Sanitization: The skill uses basic string manipulation (grep, tr) to extract data from JSON, but lacks robust validation or escaping for the processed content.

dingtalk-contact