The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external sources, specifically historical checkpoints and transcripts, using the entire search and entire explain commands.
Ingestion points: Data is pulled into the agent context via the output of shell commands in SKILL.md (e.g., entire search and entire explain).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the retrieved content as untrusted data or to ignore embedded instructions within that content.
Capability inventory: The skill allows the execution of subprocesses (entire search, entire explain, and potentially entire login).
Sanitization: No sanitization or validation of the retrieved content is performed before the agent reviews and summarizes the results for the user.

search