The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill collection presents a significant surface for indirect prompt injection due to its core functionality of processing external data.
Ingestion points: meeting-analyzer/SKILL.md parses user-uploaded meeting transcripts, while scrum-master/SKILL.md and senior-pm/SKILL.md process JSON exports from external tools.
Capability inventory: The agent is granted extensive administrative capabilities via Atlassian MCP tools, including create_user, delete_page, delete_issue, and update_field_configuration.
Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing the contents of transcripts or data files.
Sanitization: No sanitization logic is described for handling potentially malicious natural language instructions embedded within transcripts.
[COMMAND_EXECUTION]: The skill suite relies on the execution of 12 internal Python scripts to perform its primary analytical tasks.
Scripts such as senior-pm/scripts/project_health_dashboard.py and scrum-master/scripts/velocity_analyzer.py are executed via the command line.
These scripts use only Python standard library modules and operate on local data files, which is consistent with the skill's stated purpose.

pm-skills