The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from local markdown files, creating a surface for indirect prompt injection. 1. Ingestion points: Specific files in the docs/ directory including AGENT_LOG.md and PROJECT_MAP.md. 2. Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore embedded instructions within these files. 3. Capability inventory: The skill is limited to reading and writing files within docs/, .Codex/, and apps/mobile/. 4. Sanitization: Absent; there is no mention of validating or escaping content read from the documents. Despite the ingestion of potentially untrusted data from the filesystem, the risk is minimal as the skill does not employ high-risk capabilities like shell execution or network communication.

project-memory