The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as git history, pull request bodies, and issue descriptions, which are potential vectors for indirect prompt injection.\n
Ingestion points: The skill instructions in SKILL.md direct the agent to read the working tree (git status, git diff, git log) and session artefacts including files, issues, and PR bodies.\n
Boundary markers: The skill does not define or use specific boundary markers or delimiters to isolate the ingested external content from its internal instructions.\n
Capability inventory: The skill primarily serves a reporting function and does not possess capabilities for network operations, high-privilege file modifications, or remote code execution.\n
Sanitization: There are no instructions provided for sanitizing, escaping, or filtering content retrieved from git metadata or external project artefacts before it is summarized.

sitrep