The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from academic databases.
Ingestion points: The skill ingests abstracts, body snippets, and citation contexts from external papers through asta literature find, asta literature interactive, and asta papers commands.
Boundary markers: There are no explicit instructions or delimiters defined to separate retrieved academic content from agent instructions, which could allow text within a paper (e.g., a malicious abstract) to influence the agent's behavior.
Capability inventory: The skill has access to file system operations (writing results via -o, mkdir, mv) and document indexing (asta documents add).
Sanitization: No sanitization or validation of the retrieved paper content is mentioned before it is processed by the agent or indexed into the document store.

find-literature