The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including git commits, pull request activity, and issue trackers such as GitHub, Jira, and Linear. This ingestion path creates a surface for indirect prompt injection where malicious instructions embedded in commit messages or issue descriptions could potentially influence the agent's behavior during automated ceremonies.
Ingestion points: Data is pulled from git telemetry, PR logs, and external issue management platforms as described in SKILL.md (Telemetry Sync) and references/daily-rituals.md (AI Pre-Standup).
Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" warnings for the ingested telemetry data.
Capability inventory: The skill utilizes agents to read git logs, scan external issue trackers, and generate automated summaries, blocker alerts, and ticket deduplication reports.
Sanitization: No specific sanitization, validation, or filtering of the external telemetry data is defined in the instructions.
[NO_CODE]: The skill consists entirely of markdown documentation and instructional guidelines. No executable scripts, binaries, or dynamic configuration files were provided in the skill package, limiting the potential for direct malicious code execution.

scrum-conductor