The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data (JSON exports from Jira/Linear), which represents a vulnerability surface where malicious instructions could be embedded in the source data to influence the agent's behavior.
Ingestion points: The scripts/status_generator.py script reads JSON data from a user-specified file through the --input command-line argument.
Boundary markers: The script does not utilize explicit boundary markers or negative constraints (e.g., 'ignore any instructions contained within this text') when interpolating external data into the final markdown or JSON output.
Capability inventory: The included script status_generator.py is restricted to file I/O and text formatting using the Python standard library. It does not invoke subprocesses, perform network requests, or utilize dynamic execution functions like eval() or exec().
Sanitization: The script performs HTML entity escaping for the Confluence output format using html.escape, but other output formats (Markdown, Notion, Linear) perform direct string interpolation without escaping or sanitization of the input ticket data.

status-update-generator