The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external GitHub sources.
Ingestion points: The skill fetches data from gh issue list, gh pr list, and gh repo list (SKILL.md).
Boundary markers: No explicit delimiters or instructions are used to separate external data from the agent's core instructions.
Capability inventory: The skill has extensive capabilities, including Bash access, Write/Edit permissions, and the ability to execute local Python scripts (SKILL.md).
Sanitization: There is no evidence of sanitization or validation of the ingested strings before they are processed by the agent.
[COMMAND_EXECUTION]: The skill executes shell commands and local scripts to perform analysis and automation tasks.
Evidence: The skill uses Bash to invoke the gh CLI, find, and jq, and it runs several Python scripts (e.g., map-dependencies.py, portfolio-health.py) located in its {baseDir}/scripts/ directory (SKILL.md).

coordinating-projects