The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize data from Slack, Microsoft Teams, Git commit logs, and Pull Requests to generate daily standup reports and automated tickets. This ingestion of untrusted external data without explicit sanitization or boundary markers creates a risk where malicious instructions embedded in messages or commit notes could influence the agent's output or actions.
Ingestion points: Telemetry sync from Slack, Teams, Git logs, and Pull Requests (specified in SKILL.md and references/daily-rituals.md).
Boundary markers: The instructions lack delimiters or specific warnings for the agent to ignore instructions found within the ingested content.
Capability inventory: The skill has the capability to write to external project management tools (GitHub Issues, Jira, Linear) and execute scripts for synchronization (SKILL.md).
Sanitization: There are no protocols defined for escaping, validating, or filtering the content retrieved from external communication or version control systems.
[NO_CODE]: The skill documentation references functional scripts, including scripts/sync-github-to-linear.ts and scripts/generate-sprint-report.py, as well as secondary skills like track-master and docs-pro. However, the actual source code for these scripts was not provided in the skill package, preventing a full security assessment of the automation logic.

scrum-conductor