The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data which creates a vulnerability surface for indirect prompt injection attacks.\n
Ingestion points: The agent is instructed to read various files including README.md, CONTRIBUTING.md, ARCHITECTURE.md, source code files (.ts, .tsx, .js), and output from git log using commands like head, grep, and find.\n
Boundary markers: There are no instructions provided to separate the ingested content from the agent's instructions, nor are there warnings for the agent to ignore any embedded directives within the analyzed files.\n
Capability inventory: The skill utilizes local process execution capabilities including find, grep, ls, git, sort, uniq, and xargs to process and analyze the file system content.\n
Sanitization: The skill lacks any sanitization or filtering logic for the data it retrieves before the agent interprets or acts upon it.

code-review