The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to fetch data from the DBLP API and python3 with the -c flag to parse the resulting JSON. These are standard operations for querying web APIs via the command line.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to dblp.org, which is a well-known and reputable service for computer science bibliography. The data retrieved is public metadata for academic publications.
[REMOTE_CODE_EXECUTION]: Automated scanners identified a pattern where curl output is piped to python3. However, technical review confirms the Python code is hardcoded within the command and strictly used to parse and print JSON fields. It does not execute remote code from the API response.
[DATA_EXFILTRATION]: No sensitive information such as credentials, environment variables, or private files are accessed or transmitted by this skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (DBLP API). While this represents a theoretical ingestion point for untrusted data, the risk is negligible as it involves vetted academic metadata, and the skill performs no actions that could be influenced by malicious content within paper titles.

dblp-search