The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the retraction-checker-pp-cli and retraction-checker-pp-mcp tools. These are fetched via npx from the @mvanhorn/printing-press-library package and via go install from the github.com/mvanhorn/printing-press-library repository.
[DATA_EXFILTRATION]: The CLI tool supports an output delivery mechanism (--deliver webhook:<url>) which can transmit command results to an arbitrary external URL. It also features a feedback system (retraction-checker-pp-cli feedback) that can be configured to send data to a remote endpoint via the RETRACTION_CHECKER_FEEDBACK_ENDPOINT environment variable.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data when auditing bibliographies or reading lists.
Ingestion points: The scan command reads content from local files such as .bib or .txt lists (referenced in SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested files.
Capability inventory: The skill uses Read Bash to execute the CLI tool, which possesses network capabilities (webhook delivery) and local state management.
Sanitization: There is no mention of sanitization or validation of bibliographic data before it is processed by the CLI and returned to the agent context.
[COMMAND_EXECUTION]: The skill uses the Read Bash tool to invoke the retraction-checker-pp-cli binary for various scholarly verification tasks.

pp-retraction-checker