The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Automated security scans have identified a malicious URL within the skill's reference data. The domain https://fitprofessionals.net, listed as a resource for 'Fit Pro Directory' in references/directory-list.md and references/submission-tracker-template.csv, is currently blacklisted by reputation services. Additionally, the files SKILL.md and references/submission-tracker-template.csv have been flagged by file reputation scanners as containing malicious content.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting and processing untrusted product information from the user during the 'Readiness assessment' phase. This represents a potential vulnerability surface where malicious instructions could be embedded in user input.
Ingestion points: User responses to the Phase 0 readiness assessment questions in SKILL.md.
Boundary markers: No explicit delimiters or instruction isolation techniques are implemented to separate user-provided data from system instructions.
Capability inventory: The skill guides the user to execute shell commands (e.g., curl) and manage project files, which could be leveraged if the agent is influenced by injected content.
Sanitization: No sanitization or validation of user-provided product data is mentioned in the instructions.

directory-submissions