The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, including ls, cat, sed, git log, and git diff, to retrieve context from the local filesystem and version control history.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by processing untrusted external data.
Ingestion points: The agent reads content from local files located at ~/.claude/projects/.../summary.md and retrieves history from git log and git diff.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential commands embedded within the retrieved file content or commit messages.
Capability inventory: The skill has the ability to execute shell commands and read local files, which could be leveraged if the agent inadvertently follows instructions found in the ingested data.
Sanitization: The skill does not implement validation or sanitization of the data retrieved from the filesystem or Git before it is integrated into the session context.

session-summarizer