The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the dynamic context injection syntax (!command) to retrieve repository and session information at load time. Specifically, it executes git remote, git branch, git log, git diff, and gh api to populate the session context. These commands are used solely for context gathering within the local development environment and do not perform sensitive file access or network exfiltration.
[INDIRECT_PROMPT_INJECTION]: This skill has an attack surface for indirect prompt injection as it ingests untrusted data from external sources. 1. Ingestion points: Reads data from git commit logs, git diffs, and project item caches (referenced in SKILL.md). 2. Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the git history or project items. 3. Capability inventory: The skill uses Bash(gh:), Bash(git:), Read, Grep, and Glob. It is explicitly defined as read-only and does not modify projects. 4. Sanitization: There is no evidence of sanitization or escaping of the ingested text before it is processed by the agent's reasoning phase.

ghpm-suggest