The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and local files, creating a surface for indirect prompt injection where malicious instructions embedded in the content could influence the agent's behavior.
Ingestion points: The skill uses the Read tool to extract content from user-specified file paths in Step 1.2 and the WebFetch tool to retrieve data from external educational resources in Step 1.3.
Boundary markers: The instructions do not define clear delimiters or include explicit directives for the agent to ignore potentially malicious instructions embedded within the source materials.
Capability inventory: The skill has the capability to write files to the local filesystem using the Write tool and perform network operations using WebSearch and WebFetch.
Sanitization: There is no evidence of content filtering, escaping, or validation to ensure that the ingested data only contains informational content and not executable instructions.

flashcards-generator