The Agent Skills Directory

[DATA_EXFILTRATION]: The script scripts/redmine_api.py includes functionality to read local files via the --data-file and --binary-file arguments and transmit their content to a remote Redmine server via HTTP POST/PUT requests.
[CREDENTIALS_UNSAFE]: The skill automatically attempts to load sensitive configuration, including API keys and passwords, from a .env file in the current working directory. It also allows reading credentials from a specified --cred-file.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and displays data from external Redmine API responses to the agent.
Ingestion points: scripts/redmine_api.py fetches data from various Redmine API endpoints (e.g., issues, journals, comments).
Boundary markers: No explicit delimiters or instructions are used in the script output to differentiate between trusted and untrusted content.
Capability inventory: The skill possesses file-read capabilities (for config and upload data) and network-write capabilities (to send data to a user-provided Redmine URL).
Sanitization: The script performs JSON parsing but does not sanitize or escape the content of the API responses before presenting them to the agent.

redmine-api